checkpoint-40/config.json

{
  "architectures": [
    "MiMoForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_mimo.MiMoConfig",
    "AutoModel": "modeling_mimo.MiMoModel",
    "AutoModelForCausalLM": "modeling_mimo.MiMoForCausalLM"
  },
  "dtype": "bfloat16",
  "eos_token_id": 151643,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 32768,
  "max_window_layers": 32,
  "model_type": "mimo",
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "num_nextn_predict_layers": 1,
  "pad_token_id": 151643,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 640000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "tokenizer_class": [
    "Qwen2Tokenizer"
  ],
  "transformers_version": "4.57.6",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 151680
}