default_stage:
  default_modifiers:
    AWQModifier:
      config_groups:
        group_0:
          targets: [Linear]
          weights:
            num_bits: 4
            type: int
            symmetric: true
            group_size: 32
            strategy: group
            block_structure: null
            dynamic: false
            actorder: null
            observer: mse
            observer_kwargs: {}
          input_activations: null
          output_activations: null
          format: null
      targets: [Linear]
      ignore: [lm_head, 're:.*embed_tokens', 're:.*input_layernorm', 're:.*post_attention_layernorm',
        model.language_model.norm, 're:.*shared_experts.*', 're:model.language_model.layers.0.*',
        're:.*mlp.gate', 're:model.visual.*']
      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_proj$', 're:.*up_proj$']
      - smooth_layer: re:.*up_proj$
        balance_layers: ['re:.*down_proj$']
      offload_device: !!python/object/apply:torch.device [cpu]
      duo_scaling: true