finetune_sample/config.json

{
  "_name_or_path": "matsuo-lab/weblab-10b-instruction-sft",
  "architectures": [
    "GPTNeoXForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "classifier_dropout": 0.1,
  "eos_token_id": 0,
  "hidden_act": "gelu",
  "hidden_dropout": 0.0,
  "hidden_size": 4864,
  "initializer_range": 0.02,
  "intermediate_size": 19456,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "gpt_neox",
  "num_attention_heads": 38,
  "num_hidden_layers": 36,
  "rope_scaling": null,
  "rotary_emb_base": 10000,
  "rotary_pct": 0.25,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.31.0",
  "use_cache": true,
  "use_parallel_residual": true,
  "vocab_size": 50277,
  "quantization_config": {
      "quant_method":"gptq",
      "bits": 4,
      "group_size": 128,
      "damp_percent": 0.01,
      "desc_act": true,
      "sym": true,
      "true_sequential": true,
      "model_name_or_path": null,
      "model_file_base_name": null
  }
}