default_stage:
  default_modifiers:
    AWQModifier:
      config_groups:
        group_0:
          targets: [Linear]
          weights: {num_bits: 4, type: int, symmetric: false, group_size: 128, strategy: group,
            dynamic: false, observer: mse}
      targets: [Linear]
      ignore: [lm_head]
      mappings:
      - smooth_layer: re:.*input_layernorm$
        balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
      - smooth_layer: re:.*v_proj$
        balance_layers: ['re:.*o_proj$']
      - smooth_layer: re:.*post_attention_layernorm$
        balance_layers: ['re:.*gate_up_proj$']
      - smooth_layer: re:.*gate_up_proj$
        balance_layers: ['re:.*down_proj$']
      offload_device: !!python/object/apply:torch.device [cpu]