default_stage:
  default_modifiers:
    AWQModifier:
      targets: [Linear]
      ignore: [lm_head, model.layers.0.input_layernorm, model.layers.1.input_layernorm, model.layers.2.input_layernorm,
        model.layers.4.input_layernorm, model.layers.5.input_layernorm, model.layers.6.input_layernorm,
        model.layers.8.input_layernorm, model.layers.9.input_layernorm, model.layers.10.input_layernorm,
        model.layers.12.input_layernorm, model.layers.13.input_layernorm, model.layers.14.input_layernorm,
        model.layers.16.input_layernorm, model.layers.17.input_layernorm, model.layers.18.input_layernorm,
        model.layers.20.input_layernorm, model.layers.21.input_layernorm, model.layers.22.input_layernorm,
        model.layers.24.input_layernorm, model.layers.25.input_layernorm, model.layers.26.input_layernorm,
        model.layers.28.input_layernorm, model.layers.29.input_layernorm, model.layers.30.input_layernorm,
        model.layers.32.input_layernorm, model.layers.33.input_layernorm, model.layers.34.input_layernorm,
        model.layers.36.input_layernorm, model.layers.37.input_layernorm, model.layers.38.input_layernorm,
        model.layers.40.input_layernorm, model.layers.41.input_layernorm, model.layers.42.input_layernorm,
        model.layers.44.input_layernorm, model.layers.45.input_layernorm, model.layers.46.input_layernorm,
        model.layers.48.input_layernorm, model.layers.49.input_layernorm, model.layers.50.input_layernorm,
        model.layers.52.input_layernorm, model.layers.53.input_layernorm, model.layers.54.input_layernorm,
        model.layers.56.input_layernorm, model.layers.57.input_layernorm, model.layers.58.input_layernorm,
        model.layers.60.input_layernorm, model.layers.61.input_layernorm, model.layers.62.input_layernorm]
      scheme: W8A16
      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$']
      duo_scaling: true
      n_grid: 20