default_stage:
  default_modifiers:
    AWQModifier:
      mappings:
      - smooth_layer: re:.*layers\.(3|7|11|15|19|23|27|31|35|39|43|47|51|55|59|63)\.input_layernorm$
        balance_layers: ['re:.*self_attn.q_proj$', 're:.*self_attn.k_proj$', 're:.*self_attn.v_proj$']
        activation_hook_target: null
      - smooth_layer: re:.*layers\.(0|1|2|4|5|6|8|9|10|12|13|14|16|17|18|20|21|22|24|25|26|28|29|30|32|33|34|36|37|38|40|41|42|44|45|46|48|49|50|52|53|54|56|57|58|60|61|62)\.input_layernorm$
        balance_layers: ['re:.*linear_attn.in_proj_qkv$', 're:.*linear_attn.in_proj_z$', 're:.*linear_attn.in_proj_b$',
          're:.*linear_attn.in_proj_a$']
        activation_hook_target: null
      - smooth_layer: re:.*post_attention_layernorm$
        balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
        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: true
      n_grid: 20
    QuantizationModifier:
      targets: [Linear]
      ignore: [lm_head, 're:.*embed_tokens.*', 're:.*norm.*', 're:.*\.linear_attn\..*', 're:.*visual.*',
        're:.*\.mtp\..*', 're:^mtp\..*']
      scheme: W4A16
      bypass_divisibility_checks: false