| { |
| "architectures": [ |
| "MiniMaxM2ForCausalLM" |
| ], |
| "attn_type_list": [ |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1, |
| 1 |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_minimax_m2.MiniMaxM2Config", |
| "AutoModelForCausalLM": "modeling_minimax_m2.MiniMaxM2ForCausalLM" |
| }, |
| "dtype": "bfloat16", |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 3072, |
| "intermediate_size": 1536, |
| "max_position_embeddings": 196608, |
| "model_type": "minimax_m2", |
| "mtp_transformer_layers": 1, |
| "num_attention_heads": 48, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 62, |
| "num_key_value_heads": 8, |
| "num_local_experts": 256, |
| "num_mtp_modules": 3, |
| "qk_norm_type": "per_layer", |
| "quantization_config": { |
| "quant_method": "compressed-tensors", |
| "format": "mxfp4-pack-quantized", |
| "config_groups": { |
| "group_0": { |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "num_bits": 4, |
| "type": "float", |
| "strategy": "group", |
| "group_size": 32, |
| "symmetric": true |
| } |
| } |
| }, |
| "ignore": [ |
| "lm_head", |
| "model.embed_tokens", |
| "model.layers.0.block_sparse_moe.gate", |
| "model.layers.0.input_layernorm", |
| "model.layers.0.post_attention_layernorm", |
| "model.layers.0.self_attn.k_norm", |
| "model.layers.0.self_attn.k_proj", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.self_attn.q_norm", |
| "model.layers.0.self_attn.q_proj", |
| "model.layers.0.self_attn.v_proj", |
| "model.layers.1.block_sparse_moe.gate", |
| "model.layers.1.input_layernorm", |
| "model.layers.1.post_attention_layernorm", |
| "model.layers.1.self_attn.k_norm", |
| "model.layers.1.self_attn.k_proj", |
| "model.layers.1.self_attn.o_proj", |
| "model.layers.1.self_attn.q_norm", |
| "model.layers.1.self_attn.q_proj", |
| "model.layers.1.self_attn.v_proj", |
| "model.layers.10.block_sparse_moe.gate", |
| "model.layers.10.input_layernorm", |
| "model.layers.10.post_attention_layernorm", |
| "model.layers.10.self_attn.k_norm", |
| "model.layers.10.self_attn.k_proj", |
| "model.layers.10.self_attn.o_proj", |
| "model.layers.10.self_attn.q_norm", |
| "model.layers.10.self_attn.q_proj", |
| "model.layers.10.self_attn.v_proj", |
| "model.layers.11.block_sparse_moe.gate", |
| "model.layers.11.input_layernorm", |
| "model.layers.11.post_attention_layernorm", |
| "model.layers.11.self_attn.k_norm", |
| "model.layers.11.self_attn.k_proj", |
| "model.layers.11.self_attn.o_proj", |
| "model.layers.11.self_attn.q_norm", |
| "model.layers.11.self_attn.q_proj", |
| "model.layers.11.self_attn.v_proj", |
| "model.layers.12.block_sparse_moe.gate", |
| "model.layers.12.input_layernorm", |
| "model.layers.12.post_attention_layernorm", |
| "model.layers.12.self_attn.k_norm", |
| "model.layers.12.self_attn.k_proj", |
| "model.layers.12.self_attn.o_proj", |
| "model.layers.12.self_attn.q_norm", |
| "model.layers.12.self_attn.q_proj", |
| "model.layers.12.self_attn.v_proj", |
| "model.layers.13.block_sparse_moe.gate", |
| "model.layers.13.input_layernorm", |
| "model.layers.13.post_attention_layernorm", |
| "model.layers.13.self_attn.k_norm", |
| "model.layers.13.self_attn.k_proj", |
| "model.layers.13.self_attn.o_proj", |
| "model.layers.13.self_attn.q_norm", |
| "model.layers.13.self_attn.q_proj", |
| "model.layers.13.self_attn.v_proj", |
| "model.layers.14.block_sparse_moe.gate", |
| "model.layers.14.input_layernorm", |
| "model.layers.14.post_attention_layernorm", |
| "model.layers.14.self_attn.k_norm", |
| "model.layers.14.self_attn.k_proj", |
| "model.layers.14.self_attn.o_proj", |
| "model.layers.14.self_attn.q_norm", |
| "model.layers.14.self_attn.q_proj", |
| "model.layers.14.self_attn.v_proj", |
| "model.layers.15.block_sparse_moe.gate", |
| "model.layers.15.input_layernorm", |
| "model.layers.15.post_attention_layernorm", |
| "model.layers.15.self_attn.k_norm", |
| "model.layers.15.self_attn.k_proj", |
| "model.layers.15.self_attn.o_proj", |
| "model.layers.15.self_attn.q_norm", |
| "model.layers.15.self_attn.q_proj", |
| "model.layers.15.self_attn.v_proj", |
| "model.layers.16.block_sparse_moe.gate", |
| "model.layers.16.input_layernorm", |
| "model.layers.16.post_attention_layernorm", |
| "model.layers.16.self_attn.k_norm", |
| "model.layers.16.self_attn.k_proj", |
| "model.layers.16.self_attn.o_proj", |
| "model.layers.16.self_attn.q_norm", |
| "model.layers.16.self_attn.q_proj", |
| "model.layers.16.self_attn.v_proj", |
| "model.layers.17.block_sparse_moe.gate", |
| "model.layers.17.input_layernorm", |
| "model.layers.17.post_attention_layernorm", |
| "model.layers.17.self_attn.k_norm", |
| "model.layers.17.self_attn.k_proj", |
| "model.layers.17.self_attn.o_proj", |
| "model.layers.17.self_attn.q_norm", |
| "model.layers.17.self_attn.q_proj", |
| "model.layers.17.self_attn.v_proj", |
| "model.layers.18.block_sparse_moe.gate", |
| "model.layers.18.input_layernorm", |
| "model.layers.18.post_attention_layernorm", |
| "model.layers.18.self_attn.k_norm", |
| "model.layers.18.self_attn.k_proj", |
| "model.layers.18.self_attn.o_proj", |
| "model.layers.18.self_attn.q_norm", |
| "model.layers.18.self_attn.q_proj", |
| "model.layers.18.self_attn.v_proj", |
| "model.layers.19.block_sparse_moe.gate", |
| "model.layers.19.input_layernorm", |
| "model.layers.19.post_attention_layernorm", |
| "model.layers.19.self_attn.k_norm", |
| "model.layers.19.self_attn.k_proj", |
| "model.layers.19.self_attn.o_proj", |
| "model.layers.19.self_attn.q_norm", |
| "model.layers.19.self_attn.q_proj", |
| "model.layers.19.self_attn.v_proj", |
| "model.layers.2.block_sparse_moe.gate", |
| "model.layers.2.input_layernorm", |
| "model.layers.2.post_attention_layernorm", |
| "model.layers.2.self_attn.k_norm", |
| "model.layers.2.self_attn.k_proj", |
| "model.layers.2.self_attn.o_proj", |
| "model.layers.2.self_attn.q_norm", |
| "model.layers.2.self_attn.q_proj", |
| "model.layers.2.self_attn.v_proj", |
| "model.layers.20.block_sparse_moe.gate", |
| "model.layers.20.input_layernorm", |
| "model.layers.20.post_attention_layernorm", |
| "model.layers.20.self_attn.k_norm", |
| "model.layers.20.self_attn.k_proj", |
| "model.layers.20.self_attn.o_proj", |
| "model.layers.20.self_attn.q_norm", |
| "model.layers.20.self_attn.q_proj", |
| "model.layers.20.self_attn.v_proj", |
| "model.layers.21.block_sparse_moe.gate", |
| "model.layers.21.input_layernorm", |
| "model.layers.21.post_attention_layernorm", |
| "model.layers.21.self_attn.k_norm", |
| "model.layers.21.self_attn.k_proj", |
| "model.layers.21.self_attn.o_proj", |
| "model.layers.21.self_attn.q_norm", |
| "model.layers.21.self_attn.q_proj", |
| "model.layers.21.self_attn.v_proj", |
| "model.layers.22.block_sparse_moe.gate", |
| "model.layers.22.input_layernorm", |
| "model.layers.22.post_attention_layernorm", |
| "model.layers.22.self_attn.k_norm", |
| "model.layers.22.self_attn.k_proj", |
| "model.layers.22.self_attn.o_proj", |
| "model.layers.22.self_attn.q_norm", |
| "model.layers.22.self_attn.q_proj", |
| "model.layers.22.self_attn.v_proj", |
| "model.layers.23.block_sparse_moe.gate", |
| "model.layers.23.input_layernorm", |
| "model.layers.23.post_attention_layernorm", |
| "model.layers.23.self_attn.k_norm", |
| "model.layers.23.self_attn.k_proj", |
| "model.layers.23.self_attn.o_proj", |
| "model.layers.23.self_attn.q_norm", |
| "model.layers.23.self_attn.q_proj", |
| "model.layers.23.self_attn.v_proj", |
| "model.layers.24.block_sparse_moe.gate", |
| "model.layers.24.input_layernorm", |
| "model.layers.24.post_attention_layernorm", |
| "model.layers.24.self_attn.k_norm", |
| "model.layers.24.self_attn.k_proj", |
| "model.layers.24.self_attn.o_proj", |
| "model.layers.24.self_attn.q_norm", |
| "model.layers.24.self_attn.q_proj", |
| "model.layers.24.self_attn.v_proj", |
| "model.layers.25.block_sparse_moe.gate", |
| "model.layers.25.input_layernorm", |
| "model.layers.25.post_attention_layernorm", |
| "model.layers.25.self_attn.k_norm", |
| "model.layers.25.self_attn.k_proj", |
| "model.layers.25.self_attn.o_proj", |
| "model.layers.25.self_attn.q_norm", |
| "model.layers.25.self_attn.q_proj", |
| "model.layers.25.self_attn.v_proj", |
| "model.layers.26.block_sparse_moe.gate", |
| "model.layers.26.input_layernorm", |
| "model.layers.26.post_attention_layernorm", |
| "model.layers.26.self_attn.k_norm", |
| "model.layers.26.self_attn.k_proj", |
| "model.layers.26.self_attn.o_proj", |
| "model.layers.26.self_attn.q_norm", |
| "model.layers.26.self_attn.q_proj", |
| "model.layers.26.self_attn.v_proj", |
| "model.layers.27.block_sparse_moe.gate", |
| "model.layers.27.input_layernorm", |
| "model.layers.27.post_attention_layernorm", |
| "model.layers.27.self_attn.k_norm", |
| "model.layers.27.self_attn.k_proj", |
| "model.layers.27.self_attn.o_proj", |
| "model.layers.27.self_attn.q_norm", |
| "model.layers.27.self_attn.q_proj", |
| "model.layers.27.self_attn.v_proj", |
| "model.layers.28.block_sparse_moe.gate", |
| "model.layers.28.input_layernorm", |
| "model.layers.28.post_attention_layernorm", |
| "model.layers.28.self_attn.k_norm", |
| "model.layers.28.self_attn.k_proj", |
| "model.layers.28.self_attn.o_proj", |
| "model.layers.28.self_attn.q_norm", |
| "model.layers.28.self_attn.q_proj", |
| "model.layers.28.self_attn.v_proj", |
| "model.layers.29.block_sparse_moe.gate", |
| "model.layers.29.input_layernorm", |
| "model.layers.29.post_attention_layernorm", |
| "model.layers.29.self_attn.k_norm", |
| "model.layers.29.self_attn.k_proj", |
| "model.layers.29.self_attn.o_proj", |
| "model.layers.29.self_attn.q_norm", |
| "model.layers.29.self_attn.q_proj", |
| "model.layers.29.self_attn.v_proj", |
| "model.layers.3.block_sparse_moe.gate", |
| "model.layers.3.input_layernorm", |
| "model.layers.3.post_attention_layernorm", |
| "model.layers.3.self_attn.k_norm", |
| "model.layers.3.self_attn.k_proj", |
| "model.layers.3.self_attn.o_proj", |
| "model.layers.3.self_attn.q_norm", |
| "model.layers.3.self_attn.q_proj", |
| "model.layers.3.self_attn.v_proj", |
| "model.layers.30.block_sparse_moe.gate", |
| "model.layers.30.input_layernorm", |
| "model.layers.30.post_attention_layernorm", |
| "model.layers.30.self_attn.k_norm", |
| "model.layers.30.self_attn.k_proj", |
| "model.layers.30.self_attn.o_proj", |
| "model.layers.30.self_attn.q_norm", |
| "model.layers.30.self_attn.q_proj", |
| "model.layers.30.self_attn.v_proj", |
| "model.layers.31.block_sparse_moe.gate", |
| "model.layers.31.input_layernorm", |
| "model.layers.31.post_attention_layernorm", |
| "model.layers.31.self_attn.k_norm", |
| "model.layers.31.self_attn.k_proj", |
| "model.layers.31.self_attn.o_proj", |
| "model.layers.31.self_attn.q_norm", |
| "model.layers.31.self_attn.q_proj", |
| "model.layers.31.self_attn.v_proj", |
| "model.layers.32.block_sparse_moe.gate", |
| "model.layers.32.input_layernorm", |
| "model.layers.32.post_attention_layernorm", |
| "model.layers.32.self_attn.k_norm", |
| "model.layers.32.self_attn.k_proj", |
| "model.layers.32.self_attn.o_proj", |
| "model.layers.32.self_attn.q_norm", |
| "model.layers.32.self_attn.q_proj", |
| "model.layers.32.self_attn.v_proj", |
| "model.layers.33.block_sparse_moe.gate", |
| "model.layers.33.input_layernorm", |
| "model.layers.33.post_attention_layernorm", |
| "model.layers.33.self_attn.k_norm", |
| "model.layers.33.self_attn.k_proj", |
| "model.layers.33.self_attn.o_proj", |
| "model.layers.33.self_attn.q_norm", |
| "model.layers.33.self_attn.q_proj", |
| "model.layers.33.self_attn.v_proj", |
| "model.layers.34.block_sparse_moe.gate", |
| "model.layers.34.input_layernorm", |
| "model.layers.34.post_attention_layernorm", |
| "model.layers.34.self_attn.k_norm", |
| "model.layers.34.self_attn.k_proj", |
| "model.layers.34.self_attn.o_proj", |
| "model.layers.34.self_attn.q_norm", |
| "model.layers.34.self_attn.q_proj", |
| "model.layers.34.self_attn.v_proj", |
| "model.layers.35.block_sparse_moe.gate", |
| "model.layers.35.input_layernorm", |
| "model.layers.35.post_attention_layernorm", |
| "model.layers.35.self_attn.k_norm", |
| "model.layers.35.self_attn.k_proj", |
| "model.layers.35.self_attn.o_proj", |
| "model.layers.35.self_attn.q_norm", |
| "model.layers.35.self_attn.q_proj", |
| "model.layers.35.self_attn.v_proj", |
| "model.layers.36.block_sparse_moe.gate", |
| "model.layers.36.input_layernorm", |
| "model.layers.36.post_attention_layernorm", |
| "model.layers.36.self_attn.k_norm", |
| "model.layers.36.self_attn.k_proj", |
| "model.layers.36.self_attn.o_proj", |
| "model.layers.36.self_attn.q_norm", |
| "model.layers.36.self_attn.q_proj", |
| "model.layers.36.self_attn.v_proj", |
| "model.layers.37.block_sparse_moe.gate", |
| "model.layers.37.input_layernorm", |
| "model.layers.37.post_attention_layernorm", |
| "model.layers.37.self_attn.k_norm", |
| "model.layers.37.self_attn.k_proj", |
| "model.layers.37.self_attn.o_proj", |
| "model.layers.37.self_attn.q_norm", |
| "model.layers.37.self_attn.q_proj", |
| "model.layers.37.self_attn.v_proj", |
| "model.layers.38.block_sparse_moe.gate", |
| "model.layers.38.input_layernorm", |
| "model.layers.38.post_attention_layernorm", |
| "model.layers.38.self_attn.k_norm", |
| "model.layers.38.self_attn.k_proj", |
| "model.layers.38.self_attn.o_proj", |
| "model.layers.38.self_attn.q_norm", |
| "model.layers.38.self_attn.q_proj", |
| "model.layers.38.self_attn.v_proj", |
| "model.layers.39.block_sparse_moe.gate", |
| "model.layers.39.input_layernorm", |
| "model.layers.39.post_attention_layernorm", |
| "model.layers.39.self_attn.k_norm", |
| "model.layers.39.self_attn.k_proj", |
| "model.layers.39.self_attn.o_proj", |
| "model.layers.39.self_attn.q_norm", |
| "model.layers.39.self_attn.q_proj", |
| "model.layers.39.self_attn.v_proj", |
| "model.layers.4.block_sparse_moe.gate", |
| "model.layers.4.input_layernorm", |
| "model.layers.4.post_attention_layernorm", |
| "model.layers.4.self_attn.k_norm", |
| "model.layers.4.self_attn.k_proj", |
| "model.layers.4.self_attn.o_proj", |
| "model.layers.4.self_attn.q_norm", |
| "model.layers.4.self_attn.q_proj", |
| "model.layers.4.self_attn.v_proj", |
| "model.layers.40.block_sparse_moe.gate", |
| "model.layers.40.input_layernorm", |
| "model.layers.40.post_attention_layernorm", |
| "model.layers.40.self_attn.k_norm", |
| "model.layers.40.self_attn.k_proj", |
| "model.layers.40.self_attn.o_proj", |
| "model.layers.40.self_attn.q_norm", |
| "model.layers.40.self_attn.q_proj", |
| "model.layers.40.self_attn.v_proj", |
| "model.layers.41.block_sparse_moe.gate", |
| "model.layers.41.input_layernorm", |
| "model.layers.41.post_attention_layernorm", |
| "model.layers.41.self_attn.k_norm", |
| "model.layers.41.self_attn.k_proj", |
| "model.layers.41.self_attn.o_proj", |
| "model.layers.41.self_attn.q_norm", |
| "model.layers.41.self_attn.q_proj", |
| "model.layers.41.self_attn.v_proj", |
| "model.layers.42.block_sparse_moe.gate", |
| "model.layers.42.input_layernorm", |
| "model.layers.42.post_attention_layernorm", |
| "model.layers.42.self_attn.k_norm", |
| "model.layers.42.self_attn.k_proj", |
| "model.layers.42.self_attn.o_proj", |
| "model.layers.42.self_attn.q_norm", |
| "model.layers.42.self_attn.q_proj", |
| "model.layers.42.self_attn.v_proj", |
| "model.layers.43.block_sparse_moe.gate", |
| "model.layers.43.input_layernorm", |
| "model.layers.43.post_attention_layernorm", |
| "model.layers.43.self_attn.k_norm", |
| "model.layers.43.self_attn.k_proj", |
| "model.layers.43.self_attn.o_proj", |
| "model.layers.43.self_attn.q_norm", |
| "model.layers.43.self_attn.q_proj", |
| "model.layers.43.self_attn.v_proj", |
| "model.layers.44.block_sparse_moe.gate", |
| "model.layers.44.input_layernorm", |
| "model.layers.44.post_attention_layernorm", |
| "model.layers.44.self_attn.k_norm", |
| "model.layers.44.self_attn.k_proj", |
| "model.layers.44.self_attn.o_proj", |
| "model.layers.44.self_attn.q_norm", |
| "model.layers.44.self_attn.q_proj", |
| "model.layers.44.self_attn.v_proj", |
| "model.layers.45.block_sparse_moe.gate", |
| "model.layers.45.input_layernorm", |
| "model.layers.45.post_attention_layernorm", |
| "model.layers.45.self_attn.k_norm", |
| "model.layers.45.self_attn.k_proj", |
| "model.layers.45.self_attn.o_proj", |
| "model.layers.45.self_attn.q_norm", |
| "model.layers.45.self_attn.q_proj", |
| "model.layers.45.self_attn.v_proj", |
| "model.layers.46.block_sparse_moe.gate", |
| "model.layers.46.input_layernorm", |
| "model.layers.46.post_attention_layernorm", |
| "model.layers.46.self_attn.k_norm", |
| "model.layers.46.self_attn.k_proj", |
| "model.layers.46.self_attn.o_proj", |
| "model.layers.46.self_attn.q_norm", |
| "model.layers.46.self_attn.q_proj", |
| "model.layers.46.self_attn.v_proj", |
| "model.layers.47.block_sparse_moe.gate", |
| "model.layers.47.input_layernorm", |
| "model.layers.47.post_attention_layernorm", |
| "model.layers.47.self_attn.k_norm", |
| "model.layers.47.self_attn.k_proj", |
| "model.layers.47.self_attn.o_proj", |
| "model.layers.47.self_attn.q_norm", |
| "model.layers.47.self_attn.q_proj", |
| "model.layers.47.self_attn.v_proj", |
| "model.layers.48.block_sparse_moe.gate", |
| "model.layers.48.input_layernorm", |
| "model.layers.48.post_attention_layernorm", |
| "model.layers.48.self_attn.k_norm", |
| "model.layers.48.self_attn.k_proj", |
| "model.layers.48.self_attn.o_proj", |
| "model.layers.48.self_attn.q_norm", |
| "model.layers.48.self_attn.q_proj", |
| "model.layers.48.self_attn.v_proj", |
| "model.layers.49.block_sparse_moe.gate", |
| "model.layers.49.input_layernorm", |
| "model.layers.49.post_attention_layernorm", |
| "model.layers.49.self_attn.k_norm", |
| "model.layers.49.self_attn.k_proj", |
| "model.layers.49.self_attn.o_proj", |
| "model.layers.49.self_attn.q_norm", |
| "model.layers.49.self_attn.q_proj", |
| "model.layers.49.self_attn.v_proj", |
| "model.layers.5.block_sparse_moe.gate", |
| "model.layers.5.input_layernorm", |
| "model.layers.5.post_attention_layernorm", |
| "model.layers.5.self_attn.k_norm", |
| "model.layers.5.self_attn.k_proj", |
| "model.layers.5.self_attn.o_proj", |
| "model.layers.5.self_attn.q_norm", |
| "model.layers.5.self_attn.q_proj", |
| "model.layers.5.self_attn.v_proj", |
| "model.layers.50.block_sparse_moe.gate", |
| "model.layers.50.input_layernorm", |
| "model.layers.50.post_attention_layernorm", |
| "model.layers.50.self_attn.k_norm", |
| "model.layers.50.self_attn.k_proj", |
| "model.layers.50.self_attn.o_proj", |
| "model.layers.50.self_attn.q_norm", |
| "model.layers.50.self_attn.q_proj", |
| "model.layers.50.self_attn.v_proj", |
| "model.layers.51.block_sparse_moe.gate", |
| "model.layers.51.input_layernorm", |
| "model.layers.51.post_attention_layernorm", |
| "model.layers.51.self_attn.k_norm", |
| "model.layers.51.self_attn.k_proj", |
| "model.layers.51.self_attn.o_proj", |
| "model.layers.51.self_attn.q_norm", |
| "model.layers.51.self_attn.q_proj", |
| "model.layers.51.self_attn.v_proj", |
| "model.layers.52.block_sparse_moe.gate", |
| "model.layers.52.input_layernorm", |
| "model.layers.52.post_attention_layernorm", |
| "model.layers.52.self_attn.k_norm", |
| "model.layers.52.self_attn.k_proj", |
| "model.layers.52.self_attn.o_proj", |
| "model.layers.52.self_attn.q_norm", |
| "model.layers.52.self_attn.q_proj", |
| "model.layers.52.self_attn.v_proj", |
| "model.layers.53.block_sparse_moe.gate", |
| "model.layers.53.input_layernorm", |
| "model.layers.53.post_attention_layernorm", |
| "model.layers.53.self_attn.k_norm", |
| "model.layers.53.self_attn.k_proj", |
| "model.layers.53.self_attn.o_proj", |
| "model.layers.53.self_attn.q_norm", |
| "model.layers.53.self_attn.q_proj", |
| "model.layers.53.self_attn.v_proj", |
| "model.layers.54.block_sparse_moe.gate", |
| "model.layers.54.input_layernorm", |
| "model.layers.54.post_attention_layernorm", |
| "model.layers.54.self_attn.k_norm", |
| "model.layers.54.self_attn.k_proj", |
| "model.layers.54.self_attn.o_proj", |
| "model.layers.54.self_attn.q_norm", |
| "model.layers.54.self_attn.q_proj", |
| "model.layers.54.self_attn.v_proj", |
| "model.layers.55.block_sparse_moe.gate", |
| "model.layers.55.input_layernorm", |
| "model.layers.55.post_attention_layernorm", |
| "model.layers.55.self_attn.k_norm", |
| "model.layers.55.self_attn.k_proj", |
| "model.layers.55.self_attn.o_proj", |
| "model.layers.55.self_attn.q_norm", |
| "model.layers.55.self_attn.q_proj", |
| "model.layers.55.self_attn.v_proj", |
| "model.layers.56.block_sparse_moe.gate", |
| "model.layers.56.input_layernorm", |
| "model.layers.56.post_attention_layernorm", |
| "model.layers.56.self_attn.k_norm", |
| "model.layers.56.self_attn.k_proj", |
| "model.layers.56.self_attn.o_proj", |
| "model.layers.56.self_attn.q_norm", |
| "model.layers.56.self_attn.q_proj", |
| "model.layers.56.self_attn.v_proj", |
| "model.layers.57.block_sparse_moe.gate", |
| "model.layers.57.input_layernorm", |
| "model.layers.57.post_attention_layernorm", |
| "model.layers.57.self_attn.k_norm", |
| "model.layers.57.self_attn.k_proj", |
| "model.layers.57.self_attn.o_proj", |
| "model.layers.57.self_attn.q_norm", |
| "model.layers.57.self_attn.q_proj", |
| "model.layers.57.self_attn.v_proj", |
| "model.layers.58.block_sparse_moe.gate", |
| "model.layers.58.input_layernorm", |
| "model.layers.58.post_attention_layernorm", |
| "model.layers.58.self_attn.k_norm", |
| "model.layers.58.self_attn.k_proj", |
| "model.layers.58.self_attn.o_proj", |
| "model.layers.58.self_attn.q_norm", |
| "model.layers.58.self_attn.q_proj", |
| "model.layers.58.self_attn.v_proj", |
| "model.layers.59.block_sparse_moe.gate", |
| "model.layers.59.input_layernorm", |
| "model.layers.59.post_attention_layernorm", |
| "model.layers.59.self_attn.k_norm", |
| "model.layers.59.self_attn.k_proj", |
| "model.layers.59.self_attn.o_proj", |
| "model.layers.59.self_attn.q_norm", |
| "model.layers.59.self_attn.q_proj", |
| "model.layers.59.self_attn.v_proj", |
| "model.layers.6.block_sparse_moe.gate", |
| "model.layers.6.input_layernorm", |
| "model.layers.6.post_attention_layernorm", |
| "model.layers.6.self_attn.k_norm", |
| "model.layers.6.self_attn.k_proj", |
| "model.layers.6.self_attn.o_proj", |
| "model.layers.6.self_attn.q_norm", |
| "model.layers.6.self_attn.q_proj", |
| "model.layers.6.self_attn.v_proj", |
| "model.layers.60.block_sparse_moe.gate", |
| "model.layers.60.input_layernorm", |
| "model.layers.60.post_attention_layernorm", |
| "model.layers.60.self_attn.k_norm", |
| "model.layers.60.self_attn.k_proj", |
| "model.layers.60.self_attn.o_proj", |
| "model.layers.60.self_attn.q_norm", |
| "model.layers.60.self_attn.q_proj", |
| "model.layers.60.self_attn.v_proj", |
| "model.layers.61.block_sparse_moe.gate", |
| "model.layers.61.input_layernorm", |
| "model.layers.61.post_attention_layernorm", |
| "model.layers.61.self_attn.k_norm", |
| "model.layers.61.self_attn.k_proj", |
| "model.layers.61.self_attn.o_proj", |
| "model.layers.61.self_attn.q_norm", |
| "model.layers.61.self_attn.q_proj", |
| "model.layers.61.self_attn.v_proj", |
| "model.layers.7.block_sparse_moe.gate", |
| "model.layers.7.input_layernorm", |
| "model.layers.7.post_attention_layernorm", |
| "model.layers.7.self_attn.k_norm", |
| "model.layers.7.self_attn.k_proj", |
| "model.layers.7.self_attn.o_proj", |
| "model.layers.7.self_attn.q_norm", |
| "model.layers.7.self_attn.q_proj", |
| "model.layers.7.self_attn.v_proj", |
| "model.layers.8.block_sparse_moe.gate", |
| "model.layers.8.input_layernorm", |
| "model.layers.8.post_attention_layernorm", |
| "model.layers.8.self_attn.k_norm", |
| "model.layers.8.self_attn.k_proj", |
| "model.layers.8.self_attn.o_proj", |
| "model.layers.8.self_attn.q_norm", |
| "model.layers.8.self_attn.q_proj", |
| "model.layers.8.self_attn.v_proj", |
| "model.layers.9.block_sparse_moe.gate", |
| "model.layers.9.input_layernorm", |
| "model.layers.9.post_attention_layernorm", |
| "model.layers.9.self_attn.k_norm", |
| "model.layers.9.self_attn.k_proj", |
| "model.layers.9.self_attn.o_proj", |
| "model.layers.9.self_attn.q_norm", |
| "model.layers.9.self_attn.q_proj", |
| "model.layers.9.self_attn.v_proj", |
| "model.norm" |
| ] |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 5000000, |
| "rotary_dim": 64, |
| "scoring_func": "sigmoid", |
| "shared_intermediate_size": 0, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.46.1", |
| "use_cache": true, |
| "use_mtp": true, |
| "use_qk_norm": true, |
| "use_routing_bias": true, |
| "vocab_size": 200064 |
| } |
