quantization_config.json

{
  "bits": 4,
  "data_type": "int",
  "group_size": 128,
  "sym": true,
  "iters": 50,
  "lr": 0.005,
  "minmax_lr": 0.005,
  "static_attention_granularity": "tensor",
  "static_kv_granularity": "tensor",
  "to_quant_block_names": "model.layers",
  "autoround_version": "0.15.1",
  "provider": "auto-round",
  "quant_method": "awq",
  "zero_point": false,
  "version": "gemm",
  "modules_to_not_convert": [
    "lm_head"
  ]
}