{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "model_type": "llama",
  "hidden_size": 5120,
  "intermediate_size": 13824,
  "num_hidden_layers": 40,
  "num_attention_heads": 40,
  "num_key_value_heads": 40,
  "vocab_size": 32000,
  "max_position_embeddings": 4096,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "use_cache": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0
}