config.json

{
  "name_or_path": "tclf90/MiniMax-M2-REAP-162B-A10B-AWQ",
  "architectures": [
    "MiniMaxM2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "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"
  },
  "bos_token_id": null,
  "dtype": "bfloat16",
  "eos_token_id": null,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "layernorm_full_attention_beta": 1.0,
  "layernorm_linear_attention_beta": 1.0,
  "layernorm_mlp_beta": 1.0,
  "max_position_embeddings": 196608,
  "mlp_intermediate_size": 8192,
  "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": 180,
  "num_mtp_modules": 3,
  "output_router_logits": false,
  "partial_rotary_factor": 0.5,
  "qk_norm_type": "per_layer",
  "quantization_config": {
    "quant_method": "awq",
    "bits": 4,
    "group_size": 128,
    "version": "gemm",
    "zero_point": true,
    "modules_to_not_convert": [
      "model.layers.0.",
      "model.layers.1.self_attn",
      "model.layers.2.self_attn",
      "model.layers.3.self_attn",
      "model.layers.4.self_attn",
      "model.layers.5.self_attn",
      "model.layers.6.self_attn",
      "model.layers.7.self_attn",
      "model.layers.8.self_attn",
      "model.layers.9.self_attn",
      "model.layers.10.self_attn",
      "model.layers.11.self_attn",
      "model.layers.12.self_attn",
      "model.layers.13.self_attn",
      "model.layers.14.self_attn",
      "model.layers.15.self_attn",
      "model.layers.47.self_attn",
      "model.layers.48.self_attn",
      "model.layers.49.self_attn",
      "model.layers.50.self_attn",
      "model.layers.51.self_attn",
      "model.layers.52.self_attn",
      "model.layers.53.self_attn",
      "model.layers.54.self_attn",
      "model.layers.55.self_attn",
      "model.layers.56.self_attn",
      "model.layers.57.self_attn",
      "model.layers.58.self_attn",
      "model.layers.59.self_attn",
      "model.layers.60.self_attn",
      "model.layers.61.self_attn"
    ]
  },
  "rms_norm_eps": 1e-06,
  "rope_theta": 5000000,
  "rotary_dim": 64,
  "router_aux_loss_coef": 0.001,
  "router_jitter_noise": 0.0,
  "scoring_func": "sigmoid",
  "shared_intermediate_size": 0,
  "shared_moe_mode": "sigmoid",
  "sliding_window": null,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.1",
  "use_cache": true,
  "use_mtp": true,
  "use_qk_norm": true,
  "use_routing_bias": true,
  "vocab_size": 200064,
  "torch_dtype": "float16"
}