config.json

{
  "_name_or_path": "/monster/data/model/Yi-1.5-9B",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 48,
  "num_key_value_heads": 4,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "damp_percent": 0.01,
    "desc_act": false,
    "group_size": 128,
    "meta": {
      "enable_minmax_tuning": false,
      "enable_quanted_input": true,
      "iters": 1000,
      "lr": 0.001,
      "minmax_lr": 0.001,
      "packer": "autogptq:0.8.0.dev1",
      "quantizer": "intel/auto-round:0.2.0.dev",
      "scale_dtype": "float16"
    },
    "model_file_base_name": "model",
    "model_name_or_path": null,
    "quant_method": "gptq",
    "static_groups": false,
    "sym": true,
    "true_sequential": false
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 5000000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.40.2",
  "use_cache": true,
  "vocab_size": 64000
}