{
  "architectures": [
    "MiniMaxForCausalLM"
  ],
  "attention_dropout": 0.0,
  "block_size": 64,
  "bos_token_id": null,
  "dtype": "float32",
  "eos_token_id": null,
  "full_attn_alpha_factor": 3.5565588200778455,
  "full_attn_beta_factor": 1.0,
  "head_dim": 16,
  "hidden_act": "silu",
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 128,
  "layer_types": [
    "linear_attention",
    "linear_attention"
  ],
  "linear_attn_alpha_factor": 3.5565588200778455,
  "linear_attn_beta_factor": 1.0,
  "max_position_embeddings": 10240000,
  "mlp_alpha_factor": 3.5565588200778455,
  "mlp_beta_factor": 1.0,
  "model_type": "minimax",
  "num_attention_heads": 4,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 2,
  "num_key_value_heads": 2,
  "num_local_experts": 4,
  "output_router_logits": false,
  "postnorm": true,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 1000000.0,
    "rope_type": "default"
  },
  "rope_theta": 10000000,
  "rotary_dim": 64,
  "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": "5.0.0.dev0",
  "use_cache": true,
  "vocab_size": 200064
}