default_stage:
  default_modifiers:
    GPTQModifier:
      config_groups:
        group_0:
          targets: [Linear]
          weights:
            num_bits: 4
            type: float
            symmetric: true
            group_size: 16
            strategy: tensor_group
            block_structure: null
            dynamic: false
            actorder: static
            scale_dtype: torch.float8_e4m3fn
            zp_dtype: null
            observer: imatrix_mse
            observer_kwargs: {strict: true}
          input_activations:
            num_bits: 4
            type: float
            symmetric: true
            group_size: 16
            strategy: tensor_group
            block_structure: null
            dynamic: local
            actorder: null
            scale_dtype: torch.float8_e4m3fn
            zp_dtype: null
            observer: static_minmax
            observer_kwargs: {}
          output_activations: null
          format: null
      targets: [Linear]
      ignore: [lm_head, 're:.*embed.*', 're:.*vision.*', 're:.*audio.*', 're:.*router.*', 're:.*per_layer.*']
      kv_cache_scheme:
        num_bits: 8
        type: float
        symmetric: true
        group_size: null
        strategy: tensor
        block_structure: null
        dynamic: false
        actorder: null
        scale_dtype: null
        zp_dtype: null
        observer: static_minmax
        observer_kwargs: {}
      bypass_divisibility_checks: false
      requires_calibration_data: true
      block_size: 128
      dampening_frac: 0.01
      actorder: static
      offload_hessians: false