| { |
| "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", |
| "eos_token_id": 200020, |
| "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": { |
| "group_size": 64, |
| "bits": 8, |
| "mode": "affine", |
| "model.layers.0.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.5.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.5.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.5.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.49.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.49.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.49.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.50.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.50.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.50.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.51.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.51.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.51.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.52.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.52.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.52.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.53.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.53.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.53.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.54.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.54.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.54.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.55.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.55.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.55.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.56.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.56.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.56.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.57.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.57.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.57.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.58.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.58.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.58.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.59.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.59.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.59.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.60.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.60.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.60.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.61.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.61.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.61.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "lm_head": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| } |
| }, |
| "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, |
| "quantization": { |
| "group_size": 64, |
| "bits": 8, |
| "mode": "affine", |
| "model.layers.0.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.0.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.5.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.5.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.5.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.49.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.49.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.49.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.50.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.50.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.50.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.51.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.51.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.51.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.52.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.52.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.52.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.53.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.53.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.53.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.54.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.54.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.54.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.55.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.55.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.55.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.56.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.56.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.56.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.57.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.57.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.57.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.58.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.58.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.58.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.59.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.59.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.59.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.60.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.60.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.60.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.61.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.61.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "model.layers.61.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| }, |
| "lm_head": { |
| "bits": 8, |
| "group_size": 128, |
| "mode": "affine" |
| } |
| } |
| } |
