{
  "model_type": "llama",
  "architectures": ["LlamaForCausalLM"],
  "hidden_size": 2048,
  "intermediate_size": 8192,
  "num_attention_heads": 32,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "vocab_size": 128256,
  "max_position_embeddings": 131072,
  "rope_theta": 500000.0,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.0"
}