quantization_config.json

{
  "bits": 4,
  "group_size": 128,
  "sym": true,
  "data_type": "int",
  "seqlen": 40960,
  "autoround_version": "0.9.0",
  "provider": "auto-round",
  "quant_method": "awq",
  "zero_point": false,
  "version": "gemm",
  "modules_to_not_convert": [
    "model.layers.0.mlp.gate",
    "model.layers.1.mlp.gate",
    "model.layers.2.mlp.gate",
    "model.layers.3.mlp.gate",
    "model.layers.4.mlp.gate",
    "model.layers.5.mlp.gate",
    "model.layers.6.mlp.gate",
    "model.layers.7.mlp.gate",
    "model.layers.8.mlp.gate",
    "model.layers.9.mlp.gate",
    "model.layers.10.mlp.gate",
    "model.layers.11.mlp.gate",
    "model.layers.12.mlp.gate",
    "model.layers.13.mlp.gate",
    "model.layers.14.mlp.gate",
    "model.layers.15.mlp.gate",
    "model.layers.16.mlp.gate",
    "model.layers.17.mlp.gate",
    "model.layers.18.mlp.gate",
    "model.layers.19.mlp.gate",
    "model.layers.20.mlp.gate",
    "model.layers.21.mlp.gate",
    "model.layers.22.mlp.gate",
    "model.layers.23.mlp.gate",
    "model.layers.24.mlp.gate",
    "model.layers.25.mlp.gate",
    "model.layers.26.mlp.gate",
    "model.layers.27.mlp.gate",
    "lm_head"
  ]
}