{
  "_name_or_path": "rirv938/llama_8b_multihead_204m_512_tokens_step_976",
  "architectures": [
    "MultiHeadLlamaClassifier"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "multihead_llama.MultiHeadLlamaConfig",
    "AutoModel": "multihead_llama.MultiHeadLlamaClassifier"
  },
  "bos_token_id": 128000,
  "eos_token_id": 128001,
  "head_dim": 128,
  "heads": [
    {
      "name": "mcl",
      "num_labels": 2
    },
    {
      "name": "preference",
      "num_labels": 1
    },
    {
      "name": "retry",
      "num_labels": 2
    },
    {
      "name": "nsfw",
      "num_labels": 2
    }
  ],
  "hidden_act": "silu",
  "hidden_size": 4096,
  "id2label": {
    "0": "LABEL_0"
  },
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "label2id": {
    "LABEL_0": 0
  },
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "model_type": "multihead_llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 128001,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.45.2",
  "use_cache": true,
  "vocab_size": 128256
}