default_stage:
  default_modifiers:
    GPTQModifier:
      config_groups:
        attention:
          targets: ['re:.*self_attn\.(q_a_proj|q_b_proj|kv_proj|o_a_proj|o_b_proj)$', 're:.*self_attn\.compressor\.(gate_proj|kv_proj)$',
            're:.*self_attn\.compressor\.indexer\.(gate_proj|kv_proj|q_b_proj|weights_proj)$']
          weights:
            num_bits: 8
            type: float
            symmetric: true
            group_size: null
            strategy: block
            block_structure: [128, 128]
            dynamic: false
            actorder: null
            scale_dtype: null
            zp_dtype: null
            observer: memoryless_minmax
            observer_kwargs: {}
          input_activations:
            num_bits: 8
            type: float
            symmetric: true
            group_size: 128
            strategy: group
            block_structure: null
            dynamic: true
            actorder: null
            scale_dtype: null
            zp_dtype: null
            observer: null
            observer_kwargs: {}
          output_activations: null
          format: null
        experts:
          targets: ['re:.*mlp\.experts\.\d+\.(gate_proj|up_proj|down_proj)$']
          weights:
            num_bits: 4
            type: int
            symmetric: true
            group_size: 128
            strategy: group
            block_structure: null
            dynamic: false
            actorder: !!python/object/apply:compressed_tensors.quantization.quant_args.ActivationOrdering [
              static]
            scale_dtype: null
            zp_dtype: null
            observer: memoryless_minmax
            observer_kwargs: {}
          input_activations: null
          output_activations: null
          format: null
      targets: [Linear]
      ignore: [lm_head]
      bypass_divisibility_checks: false
      block_size: 128
      dampening_frac: 0.1
      actorder: static
      offload_hessians: true