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
  ],
  "bos_token_id": null,
  "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",
  "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,
  "output_router_logits": false,
  "qk_norm_type": "per_layer",
  "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": "4.46.1",
  "use_cache": true,
  "use_mtp": true,
  "use_qk_norm": true,
  "use_routing_bias": true,
  "vocab_size": 200064,
  "torch_dtype": "bfloat16",
  "auto_map": {
    "AutoConfig": "configuration_minimax_m2.MiniMaxM2Config",
    "AutoModelForCausalLM": "modeling_minimax_m2.MiniMaxM2ForCausalLM"
  }
}