config.json

{
  "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
  ],
  "attn_window_size": null,
  "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,
  "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_model_len": null,
  "max_position_embeddings": 196608,
  "mlp_intermediate_size": 8192,
  "model_type": "minimax",
  "mtp_transformer_layers": 1,
  "num_attention_heads": 48,
  "num_expert_group": null,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 62,
  "num_key_value_heads": 8,
  "num_local_experts": 256,
  "num_mtp_modules": 3,
  "output_router_logits": false,
  "pad_token_id": 200020,
  "partial_rotary_factor": 0.5,
  "qk_norm_type": "per_layer",
  "quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "desc_act": false,
    "group_size": 32,
    "lm_head": false,
    "meta": {
      "act_group_aware": true,
      "damp_auto_increment": 0.01,
      "damp_percent": 0.05,
      "mse": 0.0,
      "quantizer": [
        "gptqmodel:5.1.0-dev"
      ],
      "static_groups": false,
      "true_sequential": true,
      "uri": "https://github.com/modelcloud/gptqmodel",
      "v2": false,
      "v2_alpha": 0.25
    },
    "pack_dtype": "int32",
    "pack_impl": "cpu",
    "quant_method": "gptq",
    "sym": true
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 5000000,
  "rotary_dim": 64,
  "routed_scaling_factor": 1.0,
  "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,
  "swa_rope_theta": -1.0,
  "tie_word_embeddings": false,
  "topk_group": null,
  "transformers_version": "4.57.1",
  "use_cache": true,
  "use_grouped_topk": true,
  "use_mtp": true,
  "use_qk_norm": true,
  "use_routing_bias": true,
  "vocab_size": 200064
}