{ "schema": 1, "generated_by": { "tool": "mistralrs quantize", "mistralrs_version": "0.9.0", "git_revision": "unknown" }, "base_model": "Qwen/Qwen3.5-9B-Base", "repo_id": "mistralrs-community/Qwen3.5-9B-Base-UQFF", "uqff_version": "1.1.0", "outputs": [ { "quant": "afq2", "shards": [ "afq2-0.uqff" ], "layers": 249, "actual_counts": { "afq2": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 248320, 256 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 1024, 256 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 32, 256 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 8192, 256 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 256 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "afq2", "resolved_target": "afq2", "stored": "afq2", "shape": [ 12288, 256 ] } ] }, { "quant": "q3k", "shards": [ "q3k-0.uqff" ], "layers": 249, "actual_counts": { "q3k": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 248320, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "q3k", "resolved_target": "q3k", "stored": "q3k", "shape": [ 12288, 4096 ] } ] }, { "quant": "afq3", "shards": [ "afq3-0.uqff" ], "layers": 249, "actual_counts": { "afq3": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 248320, 384 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 1024, 384 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 32, 384 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 8192, 384 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 384 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 4096, 1152 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "afq3", "resolved_target": "afq3", "stored": "afq3", "shape": [ 12288, 384 ] } ] }, { "quant": "q4k", "shards": [ "q4k-0.uqff" ], "layers": 249, "actual_counts": { "q4k": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 248320, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "q4k", "resolved_target": "q4k", "stored": "q4k", "shape": [ 12288, 4096 ] } ] }, { "quant": "afq4", "shards": [ "afq4-0.uqff" ], "layers": 249, "actual_counts": { "afq4": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 248320, 512 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 1024, 512 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 32, 512 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 8192, 512 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 512 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 4096, 1536 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "afq4", "resolved_target": "afq4", "stored": "afq4", "shape": [ 12288, 512 ] } ] }, { "quant": "q5k", "shards": [ "q5k-0.uqff" ], "layers": 249, "actual_counts": { "q5k": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 248320, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "q5k", "resolved_target": "q5k", "stored": "q5k", "shape": [ 12288, 4096 ] } ] }, { "quant": "q6k", "shards": [ "q6k-0.uqff" ], "layers": 249, "actual_counts": { "q6k": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 248320, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "q6k", "resolved_target": "q6k", "stored": "q6k", "shape": [ 12288, 4096 ] } ] }, { "quant": "afq6", "shards": [ "afq6-0.uqff" ], "layers": 249, "actual_counts": { "afq6": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 248320, 768 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 1024, 768 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 32, 768 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 8192, 768 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 768 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 4096, 2304 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "afq6", "resolved_target": "afq6", "stored": "afq6", "shape": [ 12288, 768 ] } ] }, { "quant": "q8_0", "shards": [ "q8_0-0.uqff" ], "layers": 249, "actual_counts": { "q8_0": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 248320, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "q8_0", "resolved_target": "q8_0", "stored": "q8_0", "shape": [ 12288, 4096 ] } ] }, { "quant": "afq8", "shards": [ "afq8-0.uqff" ], "layers": 249, "actual_counts": { "afq8": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 248320, 1024 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 1024, 1024 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 32, 1024 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 8192, 1024 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 1024 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 4096, 3072 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "afq8", "resolved_target": "afq8", "stored": "afq8", "shape": [ 12288, 1024 ] } ] }, { "quant": "q2k", "shards": [ "q2k-0.uqff" ], "layers": 249, "actual_counts": { "q2k": 249 }, "fallback_count": 0, "layer_details": [ { "module": "lm_head", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 248320, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.0.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.0.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.0.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.1.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.1.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.1.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.10.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.10.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.10.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.11.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.k_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.o_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.q_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.11.self_attn.v_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.12.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.12.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.12.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.13.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.13.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.13.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.14.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.14.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.14.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.15.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.k_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.o_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.q_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.15.self_attn.v_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.16.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.16.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.16.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.17.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.17.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.17.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.18.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.18.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.18.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.19.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.k_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.o_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.q_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.19.self_attn.v_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.2.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.2.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.2.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.20.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.20.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.20.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.21.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.21.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.21.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.22.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.22.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.22.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.23.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.k_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.o_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.q_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.23.self_attn.v_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.24.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.24.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.24.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.25.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.25.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.25.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.26.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.26.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.26.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.27.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.k_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.o_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.q_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.27.self_attn.v_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.28.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.28.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.28.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.29.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.29.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.29.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.3.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.k_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.o_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.q_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.3.self_attn.v_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.30.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.30.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.30.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.31.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.k_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.o_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.q_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.31.self_attn.v_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.4.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.4.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.4.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.5.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.5.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.5.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.6.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.6.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.6.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.7.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.k_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.o_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.q_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.7.self_attn.v_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 1024, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.8.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.8.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.8.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_a", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_b", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 32, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_qkv", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 8192, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.in_proj_z", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.linear_attn.out_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 4096 ] }, { "module": "model.language_model.layers.9.mlp.down_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 4096, 12288 ] }, { "module": "model.language_model.layers.9.mlp.gate_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] }, { "module": "model.language_model.layers.9.mlp.up_proj", "default_target": "q2k", "resolved_target": "q2k", "stored": "q2k", "shape": [ 12288, 4096 ] } ] } ] }