config.json

{
    "_name_or_path": "meta-llama/Llama-2-13b-hf",
    "architectures": [
        "LlamaForCausalLM"
    ],
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 13824,
    "max_position_embeddings": 4096,
    "model_type": "llama",
    "num_attention_heads": 40,
    "num_hidden_layers": 40,
    "num_key_value_heads": 40,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.32.0.dev0",
    "use_cache": true,
    "vocab_size": 32000,
    "pad_token_id": 0,
    "quantization_config": {
      "quant_method": "awq",
      "zero_point": true,
      "q_group_size": 128,
      "w_bit": 4,
      "version": "gemm"
    }
}