LiqunMa's picture
Upload model
332b4bb verified
Raw
History Blame
24.6 kB
{
"architectures": [
"K2HorizonForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attention_gate_func": null,
"auto_map": {
"AutoConfig": "configuration_k2_horizon.K2HorizonConfig",
"AutoModel": "modeling_k2_horizon.K2HorizonModel",
"AutoModelForCausalLM": "modeling_k2_horizon.K2HorizonForCausalLM"
},
"bos_token_id": 0,
"decoder_sparse_step": 1,
"dtype": "bfloat16",
"eos_token_id": 1,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 6144,
"initializer_range": 0.02,
"intermediate_size": 16384,
"layernorm_num_groups": 1,
"max_position_embeddings": 524288,
"mlp_only_layers": [
0,
1,
2
],
"model_type": "k2_horizon",
"moe_gate_bias": true,
"moe_intermediate_size": 1792,
"mova_num_experts": 0,
"mova_num_experts_per_tok": 0,
"norm_topk_prob": true,
"num_attention_heads": 48,
"num_experts": 192,
"num_experts_per_tok": 8,
"num_hidden_layers": 61,
"num_key_value_heads": 8,
"num_shared_experts": 1,
"output_router_logits": false,
"pad_token_id": null,
"quantization_config": {
"config_groups": {
"group_0": {
"format": "float-quantized",
"input_activations": {
"actorder": null,
"block_structure": null,
"dynamic": true,
"group_size": 128,
"num_bits": 8,
"observer": null,
"observer_kwargs": {},
"scale_dtype": null,
"strategy": "group",
"symmetric": true,
"type": "float",
"zp_dtype": null
},
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"actorder": null,
"block_structure": [
128,
128
],
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "memoryless_minmax",
"observer_kwargs": {},
"scale_dtype": null,
"strategy": "block",
"symmetric": true,
"type": "float",
"zp_dtype": null
}
}
},
"format": "float-quantized",
"global_compression_ratio": null,
"ignore": [
"model.layers.0.self_attn.q_proj",
"model.layers.0.self_attn.k_proj",
"model.layers.0.self_attn.v_proj",
"model.layers.0.self_attn.o_proj",
"model.layers.0.mlp.gate_proj",
"model.layers.0.mlp.up_proj",
"model.layers.0.mlp.down_proj",
"model.layers.1.self_attn.q_proj",
"model.layers.1.self_attn.k_proj",
"model.layers.1.self_attn.v_proj",
"model.layers.1.self_attn.o_proj",
"model.layers.1.mlp.gate_proj",
"model.layers.1.mlp.up_proj",
"model.layers.1.mlp.down_proj",
"model.layers.2.self_attn.q_proj",
"model.layers.2.self_attn.k_proj",
"model.layers.2.self_attn.v_proj",
"model.layers.2.self_attn.o_proj",
"model.layers.2.mlp.gate_proj",
"model.layers.2.mlp.up_proj",
"model.layers.2.mlp.down_proj",
"model.layers.3.self_attn.q_proj",
"model.layers.3.self_attn.k_proj",
"model.layers.3.self_attn.v_proj",
"model.layers.3.self_attn.o_proj",
"model.layers.3.mlp.gate",
"model.layers.3.mlp.shared_experts.gate_proj",
"model.layers.3.mlp.shared_experts.up_proj",
"model.layers.3.mlp.shared_experts.down_proj",
"model.layers.4.self_attn.q_proj",
"model.layers.4.self_attn.k_proj",
"model.layers.4.self_attn.v_proj",
"model.layers.4.self_attn.o_proj",
"model.layers.4.mlp.gate",
"model.layers.4.mlp.shared_experts.gate_proj",
"model.layers.4.mlp.shared_experts.up_proj",
"model.layers.4.mlp.shared_experts.down_proj",
"model.layers.5.self_attn.q_proj",
"model.layers.5.self_attn.k_proj",
"model.layers.5.self_attn.v_proj",
"model.layers.5.self_attn.o_proj",
"model.layers.5.mlp.gate",
"model.layers.5.mlp.shared_experts.gate_proj",
"model.layers.5.mlp.shared_experts.up_proj",
"model.layers.5.mlp.shared_experts.down_proj",
"model.layers.6.self_attn.q_proj",
"model.layers.6.self_attn.k_proj",
"model.layers.6.self_attn.v_proj",
"model.layers.6.self_attn.o_proj",
"model.layers.6.mlp.gate",
"model.layers.6.mlp.shared_experts.gate_proj",
"model.layers.6.mlp.shared_experts.up_proj",
"model.layers.6.mlp.shared_experts.down_proj",
"model.layers.7.self_attn.q_proj",
"model.layers.7.self_attn.k_proj",
"model.layers.7.self_attn.v_proj",
"model.layers.7.self_attn.o_proj",
"model.layers.7.mlp.gate",
"model.layers.7.mlp.shared_experts.gate_proj",
"model.layers.7.mlp.shared_experts.up_proj",
"model.layers.7.mlp.shared_experts.down_proj",
"model.layers.8.self_attn.q_proj",
"model.layers.8.self_attn.k_proj",
"model.layers.8.self_attn.v_proj",
"model.layers.8.self_attn.o_proj",
"model.layers.8.mlp.gate",
"model.layers.8.mlp.shared_experts.gate_proj",
"model.layers.8.mlp.shared_experts.up_proj",
"model.layers.8.mlp.shared_experts.down_proj",
"model.layers.9.self_attn.q_proj",
"model.layers.9.self_attn.k_proj",
"model.layers.9.self_attn.v_proj",
"model.layers.9.self_attn.o_proj",
"model.layers.9.mlp.gate",
"model.layers.9.mlp.shared_experts.gate_proj",
"model.layers.9.mlp.shared_experts.up_proj",
"model.layers.9.mlp.shared_experts.down_proj",
"model.layers.10.self_attn.q_proj",
"model.layers.10.self_attn.k_proj",
"model.layers.10.self_attn.v_proj",
"model.layers.10.self_attn.o_proj",
"model.layers.10.mlp.gate",
"model.layers.10.mlp.shared_experts.gate_proj",
"model.layers.10.mlp.shared_experts.up_proj",
"model.layers.10.mlp.shared_experts.down_proj",
"model.layers.11.self_attn.q_proj",
"model.layers.11.self_attn.k_proj",
"model.layers.11.self_attn.v_proj",
"model.layers.11.self_attn.o_proj",
"model.layers.11.mlp.gate",
"model.layers.11.mlp.shared_experts.gate_proj",
"model.layers.11.mlp.shared_experts.up_proj",
"model.layers.11.mlp.shared_experts.down_proj",
"model.layers.12.self_attn.q_proj",
"model.layers.12.self_attn.k_proj",
"model.layers.12.self_attn.v_proj",
"model.layers.12.self_attn.o_proj",
"model.layers.12.mlp.gate",
"model.layers.12.mlp.shared_experts.gate_proj",
"model.layers.12.mlp.shared_experts.up_proj",
"model.layers.12.mlp.shared_experts.down_proj",
"model.layers.13.self_attn.q_proj",
"model.layers.13.self_attn.k_proj",
"model.layers.13.self_attn.v_proj",
"model.layers.13.self_attn.o_proj",
"model.layers.13.mlp.gate",
"model.layers.13.mlp.shared_experts.gate_proj",
"model.layers.13.mlp.shared_experts.up_proj",
"model.layers.13.mlp.shared_experts.down_proj",
"model.layers.14.self_attn.q_proj",
"model.layers.14.self_attn.k_proj",
"model.layers.14.self_attn.v_proj",
"model.layers.14.self_attn.o_proj",
"model.layers.14.mlp.gate",
"model.layers.14.mlp.shared_experts.gate_proj",
"model.layers.14.mlp.shared_experts.up_proj",
"model.layers.14.mlp.shared_experts.down_proj",
"model.layers.15.self_attn.q_proj",
"model.layers.15.self_attn.k_proj",
"model.layers.15.self_attn.v_proj",
"model.layers.15.self_attn.o_proj",
"model.layers.15.mlp.gate",
"model.layers.15.mlp.shared_experts.gate_proj",
"model.layers.15.mlp.shared_experts.up_proj",
"model.layers.15.mlp.shared_experts.down_proj",
"model.layers.16.self_attn.q_proj",
"model.layers.16.self_attn.k_proj",
"model.layers.16.self_attn.v_proj",
"model.layers.16.self_attn.o_proj",
"model.layers.16.mlp.gate",
"model.layers.16.mlp.shared_experts.gate_proj",
"model.layers.16.mlp.shared_experts.up_proj",
"model.layers.16.mlp.shared_experts.down_proj",
"model.layers.17.self_attn.q_proj",
"model.layers.17.self_attn.k_proj",
"model.layers.17.self_attn.v_proj",
"model.layers.17.self_attn.o_proj",
"model.layers.17.mlp.gate",
"model.layers.17.mlp.shared_experts.gate_proj",
"model.layers.17.mlp.shared_experts.up_proj",
"model.layers.17.mlp.shared_experts.down_proj",
"model.layers.18.self_attn.q_proj",
"model.layers.18.self_attn.k_proj",
"model.layers.18.self_attn.v_proj",
"model.layers.18.self_attn.o_proj",
"model.layers.18.mlp.gate",
"model.layers.18.mlp.shared_experts.gate_proj",
"model.layers.18.mlp.shared_experts.up_proj",
"model.layers.18.mlp.shared_experts.down_proj",
"model.layers.19.self_attn.q_proj",
"model.layers.19.self_attn.k_proj",
"model.layers.19.self_attn.v_proj",
"model.layers.19.self_attn.o_proj",
"model.layers.19.mlp.gate",
"model.layers.19.mlp.shared_experts.gate_proj",
"model.layers.19.mlp.shared_experts.up_proj",
"model.layers.19.mlp.shared_experts.down_proj",
"model.layers.20.self_attn.q_proj",
"model.layers.20.self_attn.k_proj",
"model.layers.20.self_attn.v_proj",
"model.layers.20.self_attn.o_proj",
"model.layers.20.mlp.gate",
"model.layers.20.mlp.shared_experts.gate_proj",
"model.layers.20.mlp.shared_experts.up_proj",
"model.layers.20.mlp.shared_experts.down_proj",
"model.layers.21.self_attn.q_proj",
"model.layers.21.self_attn.k_proj",
"model.layers.21.self_attn.v_proj",
"model.layers.21.self_attn.o_proj",
"model.layers.21.mlp.gate",
"model.layers.21.mlp.shared_experts.gate_proj",
"model.layers.21.mlp.shared_experts.up_proj",
"model.layers.21.mlp.shared_experts.down_proj",
"model.layers.22.self_attn.q_proj",
"model.layers.22.self_attn.k_proj",
"model.layers.22.self_attn.v_proj",
"model.layers.22.self_attn.o_proj",
"model.layers.22.mlp.gate",
"model.layers.22.mlp.shared_experts.gate_proj",
"model.layers.22.mlp.shared_experts.up_proj",
"model.layers.22.mlp.shared_experts.down_proj",
"model.layers.23.self_attn.q_proj",
"model.layers.23.self_attn.k_proj",
"model.layers.23.self_attn.v_proj",
"model.layers.23.self_attn.o_proj",
"model.layers.23.mlp.gate",
"model.layers.23.mlp.shared_experts.gate_proj",
"model.layers.23.mlp.shared_experts.up_proj",
"model.layers.23.mlp.shared_experts.down_proj",
"model.layers.24.self_attn.q_proj",
"model.layers.24.self_attn.k_proj",
"model.layers.24.self_attn.v_proj",
"model.layers.24.self_attn.o_proj",
"model.layers.24.mlp.gate",
"model.layers.24.mlp.shared_experts.gate_proj",
"model.layers.24.mlp.shared_experts.up_proj",
"model.layers.24.mlp.shared_experts.down_proj",
"model.layers.25.self_attn.q_proj",
"model.layers.25.self_attn.k_proj",
"model.layers.25.self_attn.v_proj",
"model.layers.25.self_attn.o_proj",
"model.layers.25.mlp.gate",
"model.layers.25.mlp.shared_experts.gate_proj",
"model.layers.25.mlp.shared_experts.up_proj",
"model.layers.25.mlp.shared_experts.down_proj",
"model.layers.26.self_attn.q_proj",
"model.layers.26.self_attn.k_proj",
"model.layers.26.self_attn.v_proj",
"model.layers.26.self_attn.o_proj",
"model.layers.26.mlp.gate",
"model.layers.26.mlp.shared_experts.gate_proj",
"model.layers.26.mlp.shared_experts.up_proj",
"model.layers.26.mlp.shared_experts.down_proj",
"model.layers.27.self_attn.q_proj",
"model.layers.27.self_attn.k_proj",
"model.layers.27.self_attn.v_proj",
"model.layers.27.self_attn.o_proj",
"model.layers.27.mlp.gate",
"model.layers.27.mlp.shared_experts.gate_proj",
"model.layers.27.mlp.shared_experts.up_proj",
"model.layers.27.mlp.shared_experts.down_proj",
"model.layers.28.self_attn.q_proj",
"model.layers.28.self_attn.k_proj",
"model.layers.28.self_attn.v_proj",
"model.layers.28.self_attn.o_proj",
"model.layers.28.mlp.gate",
"model.layers.28.mlp.shared_experts.gate_proj",
"model.layers.28.mlp.shared_experts.up_proj",
"model.layers.28.mlp.shared_experts.down_proj",
"model.layers.29.self_attn.q_proj",
"model.layers.29.self_attn.k_proj",
"model.layers.29.self_attn.v_proj",
"model.layers.29.self_attn.o_proj",
"model.layers.29.mlp.gate",
"model.layers.29.mlp.shared_experts.gate_proj",
"model.layers.29.mlp.shared_experts.up_proj",
"model.layers.29.mlp.shared_experts.down_proj",
"model.layers.30.self_attn.q_proj",
"model.layers.30.self_attn.k_proj",
"model.layers.30.self_attn.v_proj",
"model.layers.30.self_attn.o_proj",
"model.layers.30.mlp.gate",
"model.layers.30.mlp.shared_experts.gate_proj",
"model.layers.30.mlp.shared_experts.up_proj",
"model.layers.30.mlp.shared_experts.down_proj",
"model.layers.31.self_attn.q_proj",
"model.layers.31.self_attn.k_proj",
"model.layers.31.self_attn.v_proj",
"model.layers.31.self_attn.o_proj",
"model.layers.31.mlp.gate",
"model.layers.31.mlp.shared_experts.gate_proj",
"model.layers.31.mlp.shared_experts.up_proj",
"model.layers.31.mlp.shared_experts.down_proj",
"model.layers.32.self_attn.q_proj",
"model.layers.32.self_attn.k_proj",
"model.layers.32.self_attn.v_proj",
"model.layers.32.self_attn.o_proj",
"model.layers.32.mlp.gate",
"model.layers.32.mlp.shared_experts.gate_proj",
"model.layers.32.mlp.shared_experts.up_proj",
"model.layers.32.mlp.shared_experts.down_proj",
"model.layers.33.self_attn.q_proj",
"model.layers.33.self_attn.k_proj",
"model.layers.33.self_attn.v_proj",
"model.layers.33.self_attn.o_proj",
"model.layers.33.mlp.gate",
"model.layers.33.mlp.shared_experts.gate_proj",
"model.layers.33.mlp.shared_experts.up_proj",
"model.layers.33.mlp.shared_experts.down_proj",
"model.layers.34.self_attn.q_proj",
"model.layers.34.self_attn.k_proj",
"model.layers.34.self_attn.v_proj",
"model.layers.34.self_attn.o_proj",
"model.layers.34.mlp.gate",
"model.layers.34.mlp.shared_experts.gate_proj",
"model.layers.34.mlp.shared_experts.up_proj",
"model.layers.34.mlp.shared_experts.down_proj",
"model.layers.35.self_attn.q_proj",
"model.layers.35.self_attn.k_proj",
"model.layers.35.self_attn.v_proj",
"model.layers.35.self_attn.o_proj",
"model.layers.35.mlp.gate",
"model.layers.35.mlp.shared_experts.gate_proj",
"model.layers.35.mlp.shared_experts.up_proj",
"model.layers.35.mlp.shared_experts.down_proj",
"model.layers.36.self_attn.q_proj",
"model.layers.36.self_attn.k_proj",
"model.layers.36.self_attn.v_proj",
"model.layers.36.self_attn.o_proj",
"model.layers.36.mlp.gate",
"model.layers.36.mlp.shared_experts.gate_proj",
"model.layers.36.mlp.shared_experts.up_proj",
"model.layers.36.mlp.shared_experts.down_proj",
"model.layers.37.self_attn.q_proj",
"model.layers.37.self_attn.k_proj",
"model.layers.37.self_attn.v_proj",
"model.layers.37.self_attn.o_proj",
"model.layers.37.mlp.gate",
"model.layers.37.mlp.shared_experts.gate_proj",
"model.layers.37.mlp.shared_experts.up_proj",
"model.layers.37.mlp.shared_experts.down_proj",
"model.layers.38.self_attn.q_proj",
"model.layers.38.self_attn.k_proj",
"model.layers.38.self_attn.v_proj",
"model.layers.38.self_attn.o_proj",
"model.layers.38.mlp.gate",
"model.layers.38.mlp.shared_experts.gate_proj",
"model.layers.38.mlp.shared_experts.up_proj",
"model.layers.38.mlp.shared_experts.down_proj",
"model.layers.39.self_attn.q_proj",
"model.layers.39.self_attn.k_proj",
"model.layers.39.self_attn.v_proj",
"model.layers.39.self_attn.o_proj",
"model.layers.39.mlp.gate",
"model.layers.39.mlp.shared_experts.gate_proj",
"model.layers.39.mlp.shared_experts.up_proj",
"model.layers.39.mlp.shared_experts.down_proj",
"model.layers.40.self_attn.q_proj",
"model.layers.40.self_attn.k_proj",
"model.layers.40.self_attn.v_proj",
"model.layers.40.self_attn.o_proj",
"model.layers.40.mlp.gate",
"model.layers.40.mlp.shared_experts.gate_proj",
"model.layers.40.mlp.shared_experts.up_proj",
"model.layers.40.mlp.shared_experts.down_proj",
"model.layers.41.self_attn.q_proj",
"model.layers.41.self_attn.k_proj",
"model.layers.41.self_attn.v_proj",
"model.layers.41.self_attn.o_proj",
"model.layers.41.mlp.gate",
"model.layers.41.mlp.shared_experts.gate_proj",
"model.layers.41.mlp.shared_experts.up_proj",
"model.layers.41.mlp.shared_experts.down_proj",
"model.layers.42.self_attn.q_proj",
"model.layers.42.self_attn.k_proj",
"model.layers.42.self_attn.v_proj",
"model.layers.42.self_attn.o_proj",
"model.layers.42.mlp.gate",
"model.layers.42.mlp.shared_experts.gate_proj",
"model.layers.42.mlp.shared_experts.up_proj",
"model.layers.42.mlp.shared_experts.down_proj",
"model.layers.43.self_attn.q_proj",
"model.layers.43.self_attn.k_proj",
"model.layers.43.self_attn.v_proj",
"model.layers.43.self_attn.o_proj",
"model.layers.43.mlp.gate",
"model.layers.43.mlp.shared_experts.gate_proj",
"model.layers.43.mlp.shared_experts.up_proj",
"model.layers.43.mlp.shared_experts.down_proj",
"model.layers.44.self_attn.q_proj",
"model.layers.44.self_attn.k_proj",
"model.layers.44.self_attn.v_proj",
"model.layers.44.self_attn.o_proj",
"model.layers.44.mlp.gate",
"model.layers.44.mlp.shared_experts.gate_proj",
"model.layers.44.mlp.shared_experts.up_proj",
"model.layers.44.mlp.shared_experts.down_proj",
"model.layers.45.self_attn.q_proj",
"model.layers.45.self_attn.k_proj",
"model.layers.45.self_attn.v_proj",
"model.layers.45.self_attn.o_proj",
"model.layers.45.mlp.gate",
"model.layers.45.mlp.shared_experts.gate_proj",
"model.layers.45.mlp.shared_experts.up_proj",
"model.layers.45.mlp.shared_experts.down_proj",
"model.layers.46.self_attn.q_proj",
"model.layers.46.self_attn.k_proj",
"model.layers.46.self_attn.v_proj",
"model.layers.46.self_attn.o_proj",
"model.layers.46.mlp.gate",
"model.layers.46.mlp.shared_experts.gate_proj",
"model.layers.46.mlp.shared_experts.up_proj",
"model.layers.46.mlp.shared_experts.down_proj",
"model.layers.47.self_attn.q_proj",
"model.layers.47.self_attn.k_proj",
"model.layers.47.self_attn.v_proj",
"model.layers.47.self_attn.o_proj",
"model.layers.47.mlp.gate",
"model.layers.47.mlp.shared_experts.gate_proj",
"model.layers.47.mlp.shared_experts.up_proj",
"model.layers.47.mlp.shared_experts.down_proj",
"model.layers.48.self_attn.q_proj",
"model.layers.48.self_attn.k_proj",
"model.layers.48.self_attn.v_proj",
"model.layers.48.self_attn.o_proj",
"model.layers.48.mlp.gate",
"model.layers.48.mlp.shared_experts.gate_proj",
"model.layers.48.mlp.shared_experts.up_proj",
"model.layers.48.mlp.shared_experts.down_proj",
"model.layers.49.self_attn.q_proj",
"model.layers.49.self_attn.k_proj",
"model.layers.49.self_attn.v_proj",
"model.layers.49.self_attn.o_proj",
"model.layers.49.mlp.gate",
"model.layers.49.mlp.shared_experts.gate_proj",
"model.layers.49.mlp.shared_experts.up_proj",
"model.layers.49.mlp.shared_experts.down_proj",
"model.layers.50.self_attn.q_proj",
"model.layers.50.self_attn.k_proj",
"model.layers.50.self_attn.v_proj",
"model.layers.50.self_attn.o_proj",
"model.layers.50.mlp.gate",
"model.layers.50.mlp.shared_experts.gate_proj",
"model.layers.50.mlp.shared_experts.up_proj",
"model.layers.50.mlp.shared_experts.down_proj",
"model.layers.51.self_attn.q_proj",
"model.layers.51.self_attn.k_proj",
"model.layers.51.self_attn.v_proj",
"model.layers.51.self_attn.o_proj",
"model.layers.51.mlp.gate",
"model.layers.51.mlp.shared_experts.gate_proj",
"model.layers.51.mlp.shared_experts.up_proj",
"model.layers.51.mlp.shared_experts.down_proj",
"model.layers.52.self_attn.q_proj",
"model.layers.52.self_attn.k_proj",
"model.layers.52.self_attn.v_proj",
"model.layers.52.self_attn.o_proj",
"model.layers.52.mlp.gate",
"model.layers.52.mlp.shared_experts.gate_proj",
"model.layers.52.mlp.shared_experts.up_proj",
"model.layers.52.mlp.shared_experts.down_proj",
"model.layers.53.self_attn.q_proj",
"model.layers.53.self_attn.k_proj",
"model.layers.53.self_attn.v_proj",
"model.layers.53.self_attn.o_proj",
"model.layers.53.mlp.gate",
"model.layers.53.mlp.shared_experts.gate_proj",
"model.layers.53.mlp.shared_experts.up_proj",
"model.layers.53.mlp.shared_experts.down_proj",
"model.layers.54.self_attn.q_proj",
"model.layers.54.self_attn.k_proj",
"model.layers.54.self_attn.v_proj",
"model.layers.54.self_attn.o_proj",
"model.layers.54.mlp.gate",
"model.layers.54.mlp.shared_experts.gate_proj",
"model.layers.54.mlp.shared_experts.up_proj",
"model.layers.54.mlp.shared_experts.down_proj",
"model.layers.55.self_attn.q_proj",
"model.layers.55.self_attn.k_proj",
"model.layers.55.self_attn.v_proj",
"model.layers.55.self_attn.o_proj",
"model.layers.55.mlp.gate",
"model.layers.55.mlp.shared_experts.gate_proj",
"model.layers.55.mlp.shared_experts.up_proj",
"model.layers.55.mlp.shared_experts.down_proj",
"model.layers.56.self_attn.q_proj",
"model.layers.56.self_attn.k_proj",
"model.layers.56.self_attn.v_proj",
"model.layers.56.self_attn.o_proj",
"model.layers.56.mlp.gate",
"model.layers.56.mlp.shared_experts.gate_proj",
"model.layers.56.mlp.shared_experts.up_proj",
"model.layers.56.mlp.shared_experts.down_proj",
"model.layers.57.self_attn.q_proj",
"model.layers.57.self_attn.k_proj",
"model.layers.57.self_attn.v_proj",
"model.layers.57.self_attn.o_proj",
"model.layers.57.mlp.gate",
"model.layers.57.mlp.shared_experts.gate_proj",
"model.layers.57.mlp.shared_experts.up_proj",
"model.layers.57.mlp.shared_experts.down_proj",
"model.layers.58.self_attn.q_proj",
"model.layers.58.self_attn.k_proj",
"model.layers.58.self_attn.v_proj",
"model.layers.58.self_attn.o_proj",
"model.layers.58.mlp.gate",
"model.layers.58.mlp.shared_experts.gate_proj",
"model.layers.58.mlp.shared_experts.up_proj",
"model.layers.58.mlp.shared_experts.down_proj",
"model.layers.59.self_attn.q_proj",
"model.layers.59.self_attn.k_proj",
"model.layers.59.self_attn.v_proj",
"model.layers.59.self_attn.o_proj",
"model.layers.59.mlp.gate",
"model.layers.59.mlp.shared_experts.gate_proj",
"model.layers.59.mlp.shared_experts.up_proj",
"model.layers.59.mlp.shared_experts.down_proj",
"model.layers.60.self_attn.q_proj",
"model.layers.60.self_attn.k_proj",
"model.layers.60.self_attn.v_proj",
"model.layers.60.self_attn.o_proj",
"model.layers.60.mlp.gate",
"model.layers.60.mlp.shared_experts.gate_proj",
"model.layers.60.mlp.shared_experts.up_proj",
"model.layers.60.mlp.shared_experts.down_proj",
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {},
"transform_config": {},
"version": "0.18.0"
},
"query_key_norm": false,
"rms_norm_eps": 1e-06,
"rope_head_dim": 64,
"rope_parameters": {
"rope_theta": 10000000.0,
"rope_type": "default"
},
"router_aux_loss_coef": 0.001,
"router_scaling_factor": 2.5,
"router_score_func": "sigmoid",
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.13.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 250624
}