quantize_config.json

{
  "bits": 8,
  "group_size": 32,
  "desc_act": false,
  "sym": true,
  "lm_head": false,
  "quant_method": "gptq",
  "checkpoint_format": "gptq",
  "pack_dtype": "int32",
  "meta": {
    "quantizer": [
      "gptqmodel:4.0.0-dev"
    ],
    "uri": "https://github.com/modelcloud/gptqmodel",
    "damp_percent": 0.1,
    "damp_auto_increment": 0.01,
    "static_groups": false,
    "true_sequential": true,
    "mse": 0.0,
    "v2": false,
    "v2_alpha": 0.25
  },
  "memory_aware_allocation": false,
  "memory_threshold": 0.8
}