config.json

{
  "_name_or_path": "/workspace/models/llama-13b",
  "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": 2048,
  "max_sequence_length": 2048,
  "model_type": "llama",
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "pad_token_id": 0,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.28.1",
  "use_cache": true,
  "vocab_size": 32000,
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "damp_percent": 0.01,
    "desc_act": false,
    "sym": true,
    "true_sequential": true,
    "model_file_base_name": "model",
    "quant_method": "gptq"
  }
}