{ "base_model": "google/gemma-4-26B-A4B-it", "format": "dashq-packed-linear", "format_version": 1, "method": "dashq", "model_class": "image_text_to_text", "params": { "bits": 4, "group_size": 32, "low_memory_optimization": false, "moe_hessian_scope": "shared", "n_samples": 128, "scale_zero_dtype": "float16", "symmetric": false, "use_error_compensation": true, "use_optimal_shrinkage": true, "use_weighted_quantization": true }, "quantized_modules": { "model.language_model.layers.0.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.0.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.1.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.10.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 90112, "out_features": 1024, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.self_attn.o_proj": { "group_size": 32, "in_features": 8192, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 720896, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 8192, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.11.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 720896, "out_features": 8192, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.12.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.13.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.14.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.15.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.16.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 90112, "out_features": 1024, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.self_attn.o_proj": { "group_size": 32, "in_features": 8192, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 720896, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 8192, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.17.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 720896, "out_features": 8192, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.18.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.19.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.2.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.20.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.21.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.22.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 90112, "out_features": 1024, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.self_attn.o_proj": { "group_size": 32, "in_features": 8192, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 720896, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 8192, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.23.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 720896, "out_features": 8192, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.24.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.25.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.26.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.27.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.28.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 90112, "out_features": 1024, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.self_attn.o_proj": { "group_size": 32, "in_features": 8192, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 720896, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 8192, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.29.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 720896, "out_features": 8192, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.3.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.4.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 90112, "out_features": 1024, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.self_attn.o_proj": { "group_size": 32, "in_features": 8192, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 720896, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 8192, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.5.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 720896, "out_features": 8192, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.6.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.7.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.8.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.0": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.1": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.10": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.100": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.101": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.102": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.103": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.104": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.105": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.106": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.107": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.108": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.109": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.11": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.110": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.111": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.112": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.113": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.114": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.115": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.116": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.117": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.118": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.119": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.12": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.120": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.121": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.122": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.123": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.124": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.125": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.126": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.127": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.13": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.14": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.15": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.16": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.17": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.18": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.19": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.2": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.20": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.21": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.22": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.23": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.24": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.25": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.26": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.27": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.28": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.29": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.3": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.30": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.31": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.32": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.33": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.34": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.35": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.36": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.37": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.38": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.39": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.4": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.40": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.41": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.42": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.43": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.44": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.45": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.46": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.47": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.48": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.49": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.5": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.50": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.51": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.52": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.53": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.54": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.55": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.56": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.57": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.58": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.59": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.6": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.60": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.61": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.62": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.63": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.64": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.65": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.66": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.67": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.68": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.69": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.7": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.70": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.71": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.72": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.73": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.74": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.75": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.76": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.77": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.78": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.79": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.8": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.80": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.81": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.82": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.83": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.84": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.85": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.86": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.87": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.88": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.89": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.9": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.90": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.91": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.92": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.93": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.94": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.95": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.96": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.97": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.98": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.down_proj_list.99": { "group_size": 32, "in_features": 704, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 61952, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 704, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.0": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.1": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.10": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.100": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.101": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.102": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.103": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.104": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.105": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.106": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.107": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.108": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.109": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.11": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.110": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.111": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.112": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.113": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.114": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.115": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.116": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.117": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.118": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.119": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.12": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.120": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.121": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.122": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.123": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.124": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.125": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.126": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.127": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.13": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.14": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.15": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.16": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.17": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.18": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.19": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.2": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.20": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.21": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.22": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.23": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.24": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.25": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.26": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.27": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.28": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.29": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.3": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.30": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.31": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.32": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.33": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.34": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.35": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.36": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.37": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.38": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.39": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.4": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.40": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.41": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.42": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.43": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.44": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.45": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.46": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.47": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.48": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.49": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.5": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.50": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.51": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.52": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.53": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.54": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.55": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.56": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.57": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.58": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.59": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.6": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.60": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.61": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.62": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.63": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.64": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.65": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.66": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.67": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.68": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.69": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.7": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.70": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.71": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.72": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.73": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.74": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.75": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.76": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.77": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.78": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.79": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.8": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.80": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.81": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.82": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.83": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.84": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.85": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.86": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.87": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.88": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.89": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.9": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.90": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.91": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.92": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.93": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.94": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.95": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.96": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.97": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.98": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.experts.gate_up_proj_list.99": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 123904, "out_features": 1408, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.mlp.down_proj": { "group_size": 32, "in_features": 2112, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 2112, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.mlp.gate_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.mlp.up_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 185856, "out_features": 2112, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.router.proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 11264, "out_features": 128, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.self_attn.k_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.self_attn.o_proj": { "group_size": 32, "in_features": 4096, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 2816, "packing": "int4_packed_u32", "quant_in_features": 4096, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.self_attn.q_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 360448, "out_features": 4096, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" }, "model.language_model.layers.9.self_attn.v_proj": { "group_size": 32, "in_features": 2816, "linear_dtype": "bfloat16", "nbits": 4, "num_groups": 180224, "out_features": 2048, "packing": "int4_packed_u32", "quant_in_features": 2816, "runtime_backend": "torch", "scale_zero_dtype": "float16" } }, "results": { "Method": "dashq", "Model": "google/gemma-4-26B-A4B-it", "ModelSizeGB": 17.935708892, "OriginalSizeGB": 51.612009916, "PPL": 341.45819091796875, "Params": "{'bits': 4, 'group_size': 32, 'scale_zero_dtype': 'float16', 'n_samples': 128, 'moe_hessian_scope': 'shared', 'use_error_compensation': True, 'use_optimal_shrinkage': True, 'use_weighted_quantization': True, 'symmetric': False, 'low_memory_optimization': False}", "QuantTime": 2978.2115108966827, "arc_challenge": 43.68600682593857, "arc_easy": 65.61447811447812, "commonsense_qa": 40.86814086814087, "gsm8k_cot": 90.21986353297953, "hellaswag": 54.27205735909182, "lambada_openai": 22.414127692606247, "openbookqa": 32.2, "piqa": 67.7366702937976, "truthfulqa_mc2": 60.40592631233762, "winogrande": 55.485398579321235, "zeroshot_avg": 49.186978449523565 } }