default_stage:
  default_modifiers:
    AWQModifier:
      mappings:
      - smooth_layer: re:model\.language_model\.layers\.(0|1|2|3|4|6|7|8|9|10|12|13|14|15|16|18|19|20|21|22|24|25|26|27|28|30|31|32|33|34|36|37|38|39|40|42|43|44|45|46|48|49|50|51|52|54|55|56|57|58)\.input_layernorm$
        balance_layers: ['re:model\.language_model\.layers\.(0|1|2|3|4|6|7|8|9|10|12|13|14|15|16|18|19|20|21|22|24|25|26|27|28|30|31|32|33|34|36|37|38|39|40|42|43|44|45|46|48|49|50|51|52|54|55|56|57|58)\.self_attn\.q_proj$',
          're:model\.language_model\.layers\.(0|1|2|3|4|6|7|8|9|10|12|13|14|15|16|18|19|20|21|22|24|25|26|27|28|30|31|32|33|34|36|37|38|39|40|42|43|44|45|46|48|49|50|51|52|54|55|56|57|58)\.self_attn\.k_proj$',
          're:model\.language_model\.layers\.(0|1|2|3|4|6|7|8|9|10|12|13|14|15|16|18|19|20|21|22|24|25|26|27|28|30|31|32|33|34|36|37|38|39|40|42|43|44|45|46|48|49|50|51|52|54|55|56|57|58)\.self_attn\.v_proj$']
        activation_hook_target: null
      - smooth_layer: re:model\.language_model\.layers\.(0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31|32|33|34|35|36|37|38|39|40|41|42|43|44|45|46|47|48|49|50|51|52|53|54|55|56|57|58|59)\.pre_feedforward_layernorm$
        balance_layers: ['re:model\.language_model\.layers\.(0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31|32|33|34|35|36|37|38|39|40|41|42|43|44|45|46|47|48|49|50|51|52|53|54|55|56|57|58|59)\.mlp\.gate_proj$',
          're:model\.language_model\.layers\.(0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31|32|33|34|35|36|37|38|39|40|41|42|43|44|45|46|47|48|49|50|51|52|53|54|55|56|57|58|59)\.mlp\.up_proj$']
        activation_hook_target: null
      - smooth_layer: re:model\.language_model\.layers\.(0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31|32|33|34|35|36|37|38|39|40|41|42|43|44|45|46|47|48|49|50|51|52|53|54|55|56|57|58|59)\.mlp\.up_proj$
        balance_layers: ['re:model\.language_model\.layers\.(0|1|2|3|4|5|6|7|8|9|10|11|12|13|14|15|16|17|18|19|20|21|22|23|24|25|26|27|28|29|30|31|32|33|34|35|36|37|38|39|40|41|42|43|44|45|46|47|48|49|50|51|52|53|54|55|56|57|58|59)\.mlp\.down_proj$']
        activation_hook_target: null
      offload_device: cpu
      duo_scaling: true
      n_grid: 20
    QuantizationModifier:
      config_groups:
        group_0:
          targets: [Linear]
          weights:
            num_bits: 4
            type: int
            symmetric: true
            group_size: 128
            strategy: group
            block_structure: null
            dynamic: false
            actorder: null
            scale_dtype: null
            zp_dtype: null
            observer: memoryless_minmax
            observer_kwargs: {}
          input_activations: null
          output_activations: null
          format: null
      targets: [Linear]
      ignore: [lm_head, 're:.*vision_tower.*', 're:.*audio_tower.*', 're:.*video_tower.*',
        're:.*multi_modal_projector.*', 're:.*embed_vision.*', 're:.*embed_audio.*', 're:.*embed_video.*',
        're:.*image.*projection.*', 're:.*video.*projection.*', 're:.*audio.*projection.*']
      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: memoryless_minmax
        observer_kwargs: {}
      bypass_divisibility_checks: false