default_stage:
  default_modifiers:
    AWQModifier:
      targets: [Linear]
      ignore: [lm_head]
      scheme: W4A16_ASYM
      bypass_divisibility_checks: false
      mappings:
      - smooth_layer: re:.*input_layernorm$
        balance_layers: ['re:.*self_attn.q_proj$', 're:.*self_attn.k_proj$', 're:.*self_attn.v_proj$',
          're:.*mlp.gate_proj$', 're:.*mlp.up_proj$']
        activation_hook_target: null
      - smooth_layer: re:.*v_proj$
        balance_layers: ['re:.*o_proj$']
        activation_hook_target: null
      - smooth_layer: re:.*up_proj$
        balance_layers: ['re:.*down_proj$']
        activation_hook_target: null
      offload_device: !!python/object/apply:torch.device [cpu]
      duo_scaling: false
      n_grid: 10