quantization_config.json

{
  "bits": 4,
  "act_bits": 4,
  "data_type": "mx_fp",
  "act_data_type": "mx_fp",
  "group_size": 32,
  "act_group_size": 32,
  "sym": true,
  "act_sym": true,
  "act_dynamic": true,
  "autoround_version": "0.15.0",
  "block_name_to_quantize": "model.language_model.layers",
  "quant_method": "auto-round",
  "packing_format": "auto_round:llm_compressor",
  "rotation_config": {
    "algorithm": "hadamard",
    "backend": "auto",
    "block_size": 32,
    "hadamard_type": "hadamard",
    "fuse_online_to_weight": null,
    "allow_online_rotation": true
  }
}