{
  "architectures": [
    "MiniMaxM1ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attn_type_list": [
    0,
    1
  ],
  "auto_map": {
    "AutoConfig": "MiniMaxAI/MiniMax-M1-80k--configuration_minimax_m1.MiniMaxM1Config",
    "AutoModelForCausalLM": "MiniMaxAI/MiniMax-M1-80k--modeling_minimax_m1.MiniMaxM1ForCausalLM"
  },
  "head_dim": 32,
  "hidden_act": "silu",
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 128,
  "layernorm_full_attention_alpha": 3.5565588200778455,
  "layernorm_full_attention_beta": 1.0,
  "layernorm_linear_attention_alpha": 3.5565588200778455,
  "layernorm_linear_attention_beta": 1.0,
  "layernorm_mlp_alpha": 3.5565588200778455,
  "layernorm_mlp_beta": 1.0,
  "max_position_embeddings": 10240000,
  "model_type": "MiniMaxM1",
  "num_attention_heads": 2,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 2,
  "num_key_value_heads": 1,
  "num_local_experts": 8,
  "output_router_logits": false,
  "postnorm": true,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000000,
  "rotary_dim": 16,
  "router_aux_loss_coef": 0.001,
  "router_jitter_noise": 0.0,
  "shared_intermediate_size": 0,
  "shared_moe_mode": "sigmoid",
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "vocab_size": 200064
}