{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "model_type": "llama",
  "vocab_size": 32000,
  "hidden_size": 512,
  "intermediate_size": 2048,
  "num_hidden_layers": 6,
  "num_attention_heads": 8,
  "max_position_embeddings": 1024,
  "rms_norm_eps": 1e-6,
  "rope_theta": 10000.0,
  "use_cache": true,
  "torch_dtype": "float32",
  "transformers_version": "4.0.0",
  "openllm_version": "0.1.0",
  "training_steps": 10000,
  "model_size": "small"
}