default_stage:
  default_modifiers:
    AWQModifier:
      mappings:
      - smooth_layer: re:model.*layers[.](3|7|11|15|19|23|27|31)[.]input_layernorm
        balance_layers: ['re:model.*layers[.](3|7|11|15|19|23|27|31)[.]self_attn[.]q_proj',
          're:model.*layers[.](3|7|11|15|19|23|27|31)[.]self_attn[.]k_proj', 're:model.*layers[.](3|7|11|15|19|23|27|31)[.]self_attn[.]v_proj']
        activation_hook_target: null
      - smooth_layer: re:model.*layers[.](3|7|11|15|19|23|27|31)[.]self_attn[.]v_proj
        balance_layers: ['re:model.*layers[.](3|7|11|15|19|23|27|31)[.]self_attn[.]o_proj']
        activation_hook_target: null
      - smooth_layer: re:model.*post_attention_layernorm
        balance_layers: ['re:model.*mlp[.]gate_proj', 're:model.*mlp[.]up_proj']
        activation_hook_target: null
      duo_scaling: true
      n_grid: 20
    QuantizationModifier:
      config_groups:
        group_1:
          targets: [Linear]
          weights:
            num_bits: 4
            type: int
            symmetric: true
            group_size: 32
            strategy: group
            block_structure: null
            dynamic: false
            actorder: null
            scale_dtype: null
            zp_dtype: null
            observer: mse
            observer_kwargs: {}
          input_activations: null
          output_activations: null
          format: null
      targets: [Linear]
      ignore: ['re:.*embed_tokens', 're:.*linear_attn[.]in_proj_a', 're:.*linear_attn[.]in_proj_b',
        're:model[.]visual.*', 're:mtp.*', lm_head]
      bypass_divisibility_checks: false