config.json

{
  "_name_or_path": "hongyin/chat-llama2-70b-4bit",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 4096,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "quantization_config": {
    "batch_size": 1,
    "bits": 4,
    "block_name_to_quantize": "model.layers",
    "damp_percent": 0.1,
    "dataset": [
      ""
    ],
    "desc_act": false,
    "disable_exllama": false,
    "group_size": 128,
    "max_input_length": null,
    "model_seqlen": 4096,
    "module_name_preceding_first_block": [
      "model.embed_tokens"
    ],
    "pad_token_id": null,
    "quant_method": "gptq",
    "sym": true,
    "tokenizer": null,
    "true_sequential": true,
    "use_cuda_fp16": true
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.34.0",
  "use_cache": true,
  "vocab_size": 32000
}