config.json

{
  "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": 204800,
  "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": {
    "activation_scheme": "dynamic",
    "fmt": "float8_e4m3fn",
    "quant_method": "fp8",
    "weight_block_size": [
      128,
      128
    ],
    "modules_to_not_convert": [
      "gate",
      "e_score_correction_bias",
      "lm_head"
    ]
  },
  "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
}