{
  "architectures": [
    "LLaMAForCausalLM"
  ],
  "hidden_size": 4096,
  "intermediate_size": 11008,
  "max_position_embeddings": 2048,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "rope_scaling": null,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "transformers_version": "4.29.0",
  "use_cache": true,
  "vocab_size": 32000
}