{
  "architectures": [
    "MiniMaxForCausalLM"
  ],
  "attention_dropout": 0.0,
  "layer_types": [
    "linear_attention",
    "full_attention",
    "linear_attention",
    "full_attention"
  ],
  "auto_map": {
    "AutoConfig": "configuration_minimax.MiniMaxConfig",
    "AutoModelForCausalLM": "modeling_minimax.MiniMaxForCausalLM"
  },
  "bos_token_id": null,
  "eos_token_id": 200020,
  "head_dim": 32,
  "hidden_act": "silu",
  "hidden_size": 256,
  "initializer_range": 0.02,
  "intermediate_size": 512,
  "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": 1024,
  "model_type": "minimax",
  "num_attention_heads": 4,
  "num_experts_per_tok": 1,
  "num_hidden_layers": 4,
  "num_key_value_heads": 2,
  "num_local_experts": 2,
  "output_router_logits": false,
  "postnorm": true,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000,
  "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": false,
  "transformers_version": "4.45.2",
  "use_cache": true,
  "vocab_size": 200064
}