{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "model_type": "llama",
  "hidden_size": 256,
  "intermediate_size": 1024,
  "num_attention_heads": 8,
  "num_hidden_layers": 6,
  "num_key_value_heads": 4,
  "vocab_size": 50257,
  "rms_norm_eps": 1e-06,
  "max_position_embeddings": 512,
  "torch_dtype": "float32",
  "transformers_version": "4.31.0"
}