quantization_config.json

{
  "bits": 4,
  "group_size": 128,
  "sym": true,
  "data_type": "int",
  "enable_quanted_input": true,
  "enable_minmax_tuning": true,
  "seqlen": 2048,
  "batch_size": 8,
  "scale_dtype": "torch.float16",
  "lr": 0.001,
  "minmax_lr": 0.001,
  "gradient_accumulate_steps": 1,
  "iters": 1000,
  "amp": true,
  "nsamples": 512,
  "low_gpu_mem_usage": false,
  "to_quant_block_names": [
    [
      "model.layers.0",
      "model.layers.1",
      "model.layers.2",
      "model.layers.3",
      "model.layers.4",
      "model.layers.5",
      "model.layers.6",
      "model.layers.7",
      "model.layers.8",
      "model.layers.9",
      "model.layers.10",
      "model.layers.11",
      "model.layers.12",
      "model.layers.13",
      "model.layers.14",
      "model.layers.15",
      "model.layers.16",
      "model.layers.17",
      "model.layers.18",
      "model.layers.19",
      "model.layers.20",
      "model.layers.21",
      "model.layers.22",
      "model.layers.23",
      "model.layers.24",
      "model.layers.25",
      "model.layers.26",
      "model.layers.27",
      "model.layers.28",
      "model.layers.29",
      "model.layers.30",
      "model.layers.31"
    ]
  ],
  "enable_norm_bias_tuning": false,
  "dataset": "NeelNanda/pile-10k",
  "autoround_version": "0.4.1",
  "quant_method": "intel/auto-round",
  "backend": "auto_round:gptq:exllamav2"
}