{
    "architectures": [
        "LlamaForCausalLM"
    ],
    "hidden_size": 2048,
    "intermediate_size": 5632,
    "max_position_embeddings": 16384,
    "model_type": "llama",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "num_key_value_heads": 16,
    "quantization": {
        "group_size": 64,
        "bits": 4
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4
    },
    "rms_norm_eps": 1e-06,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.33.1",
    "vocab_size": 102400
}