default_stage: default_modifiers: AWQModifier: 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.*'] scheme: W4A16 bypass_divisibility_checks: false mappings: - smooth_layer: model.language_model.layers.0.input_layernorm balance_layers: [model.language_model.layers.0.self_attn.q_proj, model.language_model.layers.0.self_attn.k_proj, model.language_model.layers.0.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.0.pre_feedforward_layernorm balance_layers: [model.language_model.layers.0.mlp.gate_proj, model.language_model.layers.0.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.0.mlp.up_proj balance_layers: [model.language_model.layers.0.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.1.input_layernorm balance_layers: [model.language_model.layers.1.self_attn.q_proj, model.language_model.layers.1.self_attn.k_proj, model.language_model.layers.1.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.1.pre_feedforward_layernorm balance_layers: [model.language_model.layers.1.mlp.gate_proj, model.language_model.layers.1.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.1.mlp.up_proj balance_layers: [model.language_model.layers.1.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.2.input_layernorm balance_layers: [model.language_model.layers.2.self_attn.q_proj, model.language_model.layers.2.self_attn.k_proj, model.language_model.layers.2.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.2.pre_feedforward_layernorm balance_layers: [model.language_model.layers.2.mlp.gate_proj, model.language_model.layers.2.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.2.mlp.up_proj balance_layers: [model.language_model.layers.2.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.3.input_layernorm balance_layers: [model.language_model.layers.3.self_attn.q_proj, model.language_model.layers.3.self_attn.k_proj, model.language_model.layers.3.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.3.pre_feedforward_layernorm balance_layers: [model.language_model.layers.3.mlp.gate_proj, model.language_model.layers.3.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.3.mlp.up_proj balance_layers: [model.language_model.layers.3.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.4.input_layernorm balance_layers: [model.language_model.layers.4.self_attn.q_proj, model.language_model.layers.4.self_attn.k_proj, model.language_model.layers.4.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.4.pre_feedforward_layernorm balance_layers: [model.language_model.layers.4.mlp.gate_proj, model.language_model.layers.4.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.4.mlp.up_proj balance_layers: [model.language_model.layers.4.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.5.pre_feedforward_layernorm balance_layers: [model.language_model.layers.5.mlp.gate_proj, model.language_model.layers.5.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.5.mlp.up_proj balance_layers: [model.language_model.layers.5.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.6.input_layernorm balance_layers: [model.language_model.layers.6.self_attn.q_proj, model.language_model.layers.6.self_attn.k_proj, model.language_model.layers.6.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.6.pre_feedforward_layernorm balance_layers: [model.language_model.layers.6.mlp.gate_proj, model.language_model.layers.6.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.6.mlp.up_proj balance_layers: [model.language_model.layers.6.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.7.input_layernorm balance_layers: [model.language_model.layers.7.self_attn.q_proj, model.language_model.layers.7.self_attn.k_proj, model.language_model.layers.7.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.7.pre_feedforward_layernorm balance_layers: [model.language_model.layers.7.mlp.gate_proj, model.language_model.layers.7.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.7.mlp.up_proj balance_layers: [model.language_model.layers.7.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.8.input_layernorm balance_layers: [model.language_model.layers.8.self_attn.q_proj, model.language_model.layers.8.self_attn.k_proj, model.language_model.layers.8.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.8.pre_feedforward_layernorm balance_layers: [model.language_model.layers.8.mlp.gate_proj, model.language_model.layers.8.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.8.mlp.up_proj balance_layers: [model.language_model.layers.8.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.9.input_layernorm balance_layers: [model.language_model.layers.9.self_attn.q_proj, model.language_model.layers.9.self_attn.k_proj, model.language_model.layers.9.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.9.pre_feedforward_layernorm balance_layers: [model.language_model.layers.9.mlp.gate_proj, model.language_model.layers.9.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.9.mlp.up_proj balance_layers: [model.language_model.layers.9.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.10.input_layernorm balance_layers: [model.language_model.layers.10.self_attn.q_proj, model.language_model.layers.10.self_attn.k_proj, model.language_model.layers.10.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.10.pre_feedforward_layernorm balance_layers: [model.language_model.layers.10.mlp.gate_proj, model.language_model.layers.10.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.10.mlp.up_proj balance_layers: [model.language_model.layers.10.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.11.pre_feedforward_layernorm balance_layers: [model.language_model.layers.11.mlp.gate_proj, model.language_model.layers.11.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.11.mlp.up_proj balance_layers: [model.language_model.layers.11.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.12.input_layernorm balance_layers: [model.language_model.layers.12.self_attn.q_proj, model.language_model.layers.12.self_attn.k_proj, model.language_model.layers.12.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.12.pre_feedforward_layernorm balance_layers: [model.language_model.layers.12.mlp.gate_proj, model.language_model.layers.12.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.12.mlp.up_proj balance_layers: [model.language_model.layers.12.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.13.input_layernorm balance_layers: [model.language_model.layers.13.self_attn.q_proj, model.language_model.layers.13.self_attn.k_proj, model.language_model.layers.13.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.13.pre_feedforward_layernorm balance_layers: [model.language_model.layers.13.mlp.gate_proj, model.language_model.layers.13.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.13.mlp.up_proj balance_layers: [model.language_model.layers.13.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.14.input_layernorm balance_layers: [model.language_model.layers.14.self_attn.q_proj, model.language_model.layers.14.self_attn.k_proj, model.language_model.layers.14.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.14.pre_feedforward_layernorm balance_layers: [model.language_model.layers.14.mlp.gate_proj, model.language_model.layers.14.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.14.mlp.up_proj balance_layers: [model.language_model.layers.14.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.15.input_layernorm balance_layers: [model.language_model.layers.15.self_attn.q_proj, model.language_model.layers.15.self_attn.k_proj, model.language_model.layers.15.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.15.pre_feedforward_layernorm balance_layers: [model.language_model.layers.15.mlp.gate_proj, model.language_model.layers.15.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.15.mlp.up_proj balance_layers: [model.language_model.layers.15.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.16.input_layernorm balance_layers: [model.language_model.layers.16.self_attn.q_proj, model.language_model.layers.16.self_attn.k_proj, model.language_model.layers.16.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.16.pre_feedforward_layernorm balance_layers: [model.language_model.layers.16.mlp.gate_proj, model.language_model.layers.16.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.16.mlp.up_proj balance_layers: [model.language_model.layers.16.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.17.pre_feedforward_layernorm balance_layers: [model.language_model.layers.17.mlp.gate_proj, model.language_model.layers.17.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.17.mlp.up_proj balance_layers: [model.language_model.layers.17.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.18.input_layernorm balance_layers: [model.language_model.layers.18.self_attn.q_proj, model.language_model.layers.18.self_attn.k_proj, model.language_model.layers.18.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.18.pre_feedforward_layernorm balance_layers: [model.language_model.layers.18.mlp.gate_proj, model.language_model.layers.18.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.18.mlp.up_proj balance_layers: [model.language_model.layers.18.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.19.input_layernorm balance_layers: [model.language_model.layers.19.self_attn.q_proj, model.language_model.layers.19.self_attn.k_proj, model.language_model.layers.19.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.19.pre_feedforward_layernorm balance_layers: [model.language_model.layers.19.mlp.gate_proj, model.language_model.layers.19.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.19.mlp.up_proj balance_layers: [model.language_model.layers.19.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.20.input_layernorm balance_layers: [model.language_model.layers.20.self_attn.q_proj, model.language_model.layers.20.self_attn.k_proj, model.language_model.layers.20.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.20.pre_feedforward_layernorm balance_layers: [model.language_model.layers.20.mlp.gate_proj, model.language_model.layers.20.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.20.mlp.up_proj balance_layers: [model.language_model.layers.20.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.21.input_layernorm balance_layers: [model.language_model.layers.21.self_attn.q_proj, model.language_model.layers.21.self_attn.k_proj, model.language_model.layers.21.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.21.pre_feedforward_layernorm balance_layers: [model.language_model.layers.21.mlp.gate_proj, model.language_model.layers.21.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.21.mlp.up_proj balance_layers: [model.language_model.layers.21.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.22.input_layernorm balance_layers: [model.language_model.layers.22.self_attn.q_proj, model.language_model.layers.22.self_attn.k_proj, model.language_model.layers.22.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.22.pre_feedforward_layernorm balance_layers: [model.language_model.layers.22.mlp.gate_proj, model.language_model.layers.22.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.22.mlp.up_proj balance_layers: [model.language_model.layers.22.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.23.pre_feedforward_layernorm balance_layers: [model.language_model.layers.23.mlp.gate_proj, model.language_model.layers.23.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.23.mlp.up_proj balance_layers: [model.language_model.layers.23.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.24.input_layernorm balance_layers: [model.language_model.layers.24.self_attn.q_proj, model.language_model.layers.24.self_attn.k_proj, model.language_model.layers.24.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.24.pre_feedforward_layernorm balance_layers: [model.language_model.layers.24.mlp.gate_proj, model.language_model.layers.24.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.24.mlp.up_proj balance_layers: [model.language_model.layers.24.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.25.input_layernorm balance_layers: [model.language_model.layers.25.self_attn.q_proj, model.language_model.layers.25.self_attn.k_proj, model.language_model.layers.25.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.25.pre_feedforward_layernorm balance_layers: [model.language_model.layers.25.mlp.gate_proj, model.language_model.layers.25.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.25.mlp.up_proj balance_layers: [model.language_model.layers.25.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.26.input_layernorm balance_layers: [model.language_model.layers.26.self_attn.q_proj, model.language_model.layers.26.self_attn.k_proj, model.language_model.layers.26.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.26.pre_feedforward_layernorm balance_layers: [model.language_model.layers.26.mlp.gate_proj, model.language_model.layers.26.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.26.mlp.up_proj balance_layers: [model.language_model.layers.26.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.27.input_layernorm balance_layers: [model.language_model.layers.27.self_attn.q_proj, model.language_model.layers.27.self_attn.k_proj, model.language_model.layers.27.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.27.pre_feedforward_layernorm balance_layers: [model.language_model.layers.27.mlp.gate_proj, model.language_model.layers.27.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.27.mlp.up_proj balance_layers: [model.language_model.layers.27.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.28.input_layernorm balance_layers: [model.language_model.layers.28.self_attn.q_proj, model.language_model.layers.28.self_attn.k_proj, model.language_model.layers.28.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.28.pre_feedforward_layernorm balance_layers: [model.language_model.layers.28.mlp.gate_proj, model.language_model.layers.28.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.28.mlp.up_proj balance_layers: [model.language_model.layers.28.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.29.pre_feedforward_layernorm balance_layers: [model.language_model.layers.29.mlp.gate_proj, model.language_model.layers.29.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.29.mlp.up_proj balance_layers: [model.language_model.layers.29.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.30.input_layernorm balance_layers: [model.language_model.layers.30.self_attn.q_proj, model.language_model.layers.30.self_attn.k_proj, model.language_model.layers.30.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.30.pre_feedforward_layernorm balance_layers: [model.language_model.layers.30.mlp.gate_proj, model.language_model.layers.30.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.30.mlp.up_proj balance_layers: [model.language_model.layers.30.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.31.input_layernorm balance_layers: [model.language_model.layers.31.self_attn.q_proj, model.language_model.layers.31.self_attn.k_proj, model.language_model.layers.31.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.31.pre_feedforward_layernorm balance_layers: [model.language_model.layers.31.mlp.gate_proj, model.language_model.layers.31.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.31.mlp.up_proj balance_layers: [model.language_model.layers.31.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.32.input_layernorm balance_layers: [model.language_model.layers.32.self_attn.q_proj, model.language_model.layers.32.self_attn.k_proj, model.language_model.layers.32.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.32.pre_feedforward_layernorm balance_layers: [model.language_model.layers.32.mlp.gate_proj, model.language_model.layers.32.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.32.mlp.up_proj balance_layers: [model.language_model.layers.32.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.33.input_layernorm balance_layers: [model.language_model.layers.33.self_attn.q_proj, model.language_model.layers.33.self_attn.k_proj, model.language_model.layers.33.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.33.pre_feedforward_layernorm balance_layers: [model.language_model.layers.33.mlp.gate_proj, model.language_model.layers.33.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.33.mlp.up_proj balance_layers: [model.language_model.layers.33.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.34.input_layernorm balance_layers: [model.language_model.layers.34.self_attn.q_proj, model.language_model.layers.34.self_attn.k_proj, model.language_model.layers.34.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.34.pre_feedforward_layernorm balance_layers: [model.language_model.layers.34.mlp.gate_proj, model.language_model.layers.34.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.34.mlp.up_proj balance_layers: [model.language_model.layers.34.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.35.pre_feedforward_layernorm balance_layers: [model.language_model.layers.35.mlp.gate_proj, model.language_model.layers.35.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.35.mlp.up_proj balance_layers: [model.language_model.layers.35.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.36.input_layernorm balance_layers: [model.language_model.layers.36.self_attn.q_proj, model.language_model.layers.36.self_attn.k_proj, model.language_model.layers.36.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.36.pre_feedforward_layernorm balance_layers: [model.language_model.layers.36.mlp.gate_proj, model.language_model.layers.36.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.36.mlp.up_proj balance_layers: [model.language_model.layers.36.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.37.input_layernorm balance_layers: [model.language_model.layers.37.self_attn.q_proj, model.language_model.layers.37.self_attn.k_proj, model.language_model.layers.37.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.37.pre_feedforward_layernorm balance_layers: [model.language_model.layers.37.mlp.gate_proj, model.language_model.layers.37.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.37.mlp.up_proj balance_layers: [model.language_model.layers.37.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.38.input_layernorm balance_layers: [model.language_model.layers.38.self_attn.q_proj, model.language_model.layers.38.self_attn.k_proj, model.language_model.layers.38.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.38.pre_feedforward_layernorm balance_layers: [model.language_model.layers.38.mlp.gate_proj, model.language_model.layers.38.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.38.mlp.up_proj balance_layers: [model.language_model.layers.38.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.39.input_layernorm balance_layers: [model.language_model.layers.39.self_attn.q_proj, model.language_model.layers.39.self_attn.k_proj, model.language_model.layers.39.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.39.pre_feedforward_layernorm balance_layers: [model.language_model.layers.39.mlp.gate_proj, model.language_model.layers.39.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.39.mlp.up_proj balance_layers: [model.language_model.layers.39.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.40.input_layernorm balance_layers: [model.language_model.layers.40.self_attn.q_proj, model.language_model.layers.40.self_attn.k_proj, model.language_model.layers.40.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.40.pre_feedforward_layernorm balance_layers: [model.language_model.layers.40.mlp.gate_proj, model.language_model.layers.40.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.40.mlp.up_proj balance_layers: [model.language_model.layers.40.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.41.pre_feedforward_layernorm balance_layers: [model.language_model.layers.41.mlp.gate_proj, model.language_model.layers.41.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.41.mlp.up_proj balance_layers: [model.language_model.layers.41.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.42.input_layernorm balance_layers: [model.language_model.layers.42.self_attn.q_proj, model.language_model.layers.42.self_attn.k_proj, model.language_model.layers.42.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.42.pre_feedforward_layernorm balance_layers: [model.language_model.layers.42.mlp.gate_proj, model.language_model.layers.42.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.42.mlp.up_proj balance_layers: [model.language_model.layers.42.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.43.input_layernorm balance_layers: [model.language_model.layers.43.self_attn.q_proj, model.language_model.layers.43.self_attn.k_proj, model.language_model.layers.43.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.43.pre_feedforward_layernorm balance_layers: [model.language_model.layers.43.mlp.gate_proj, model.language_model.layers.43.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.43.mlp.up_proj balance_layers: [model.language_model.layers.43.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.44.input_layernorm balance_layers: [model.language_model.layers.44.self_attn.q_proj, model.language_model.layers.44.self_attn.k_proj, model.language_model.layers.44.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.44.pre_feedforward_layernorm balance_layers: [model.language_model.layers.44.mlp.gate_proj, model.language_model.layers.44.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.44.mlp.up_proj balance_layers: [model.language_model.layers.44.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.45.input_layernorm balance_layers: [model.language_model.layers.45.self_attn.q_proj, model.language_model.layers.45.self_attn.k_proj, model.language_model.layers.45.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.45.pre_feedforward_layernorm balance_layers: [model.language_model.layers.45.mlp.gate_proj, model.language_model.layers.45.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.45.mlp.up_proj balance_layers: [model.language_model.layers.45.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.46.input_layernorm balance_layers: [model.language_model.layers.46.self_attn.q_proj, model.language_model.layers.46.self_attn.k_proj, model.language_model.layers.46.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.46.pre_feedforward_layernorm balance_layers: [model.language_model.layers.46.mlp.gate_proj, model.language_model.layers.46.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.46.mlp.up_proj balance_layers: [model.language_model.layers.46.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.47.pre_feedforward_layernorm balance_layers: [model.language_model.layers.47.mlp.gate_proj, model.language_model.layers.47.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.47.mlp.up_proj balance_layers: [model.language_model.layers.47.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.48.input_layernorm balance_layers: [model.language_model.layers.48.self_attn.q_proj, model.language_model.layers.48.self_attn.k_proj, model.language_model.layers.48.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.48.pre_feedforward_layernorm balance_layers: [model.language_model.layers.48.mlp.gate_proj, model.language_model.layers.48.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.48.mlp.up_proj balance_layers: [model.language_model.layers.48.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.49.input_layernorm balance_layers: [model.language_model.layers.49.self_attn.q_proj, model.language_model.layers.49.self_attn.k_proj, model.language_model.layers.49.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.49.pre_feedforward_layernorm balance_layers: [model.language_model.layers.49.mlp.gate_proj, model.language_model.layers.49.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.49.mlp.up_proj balance_layers: [model.language_model.layers.49.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.50.input_layernorm balance_layers: [model.language_model.layers.50.self_attn.q_proj, model.language_model.layers.50.self_attn.k_proj, model.language_model.layers.50.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.50.pre_feedforward_layernorm balance_layers: [model.language_model.layers.50.mlp.gate_proj, model.language_model.layers.50.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.50.mlp.up_proj balance_layers: [model.language_model.layers.50.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.51.input_layernorm balance_layers: [model.language_model.layers.51.self_attn.q_proj, model.language_model.layers.51.self_attn.k_proj, model.language_model.layers.51.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.51.pre_feedforward_layernorm balance_layers: [model.language_model.layers.51.mlp.gate_proj, model.language_model.layers.51.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.51.mlp.up_proj balance_layers: [model.language_model.layers.51.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.52.input_layernorm balance_layers: [model.language_model.layers.52.self_attn.q_proj, model.language_model.layers.52.self_attn.k_proj, model.language_model.layers.52.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.52.pre_feedforward_layernorm balance_layers: [model.language_model.layers.52.mlp.gate_proj, model.language_model.layers.52.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.52.mlp.up_proj balance_layers: [model.language_model.layers.52.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.53.pre_feedforward_layernorm balance_layers: [model.language_model.layers.53.mlp.gate_proj, model.language_model.layers.53.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.53.mlp.up_proj balance_layers: [model.language_model.layers.53.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.54.input_layernorm balance_layers: [model.language_model.layers.54.self_attn.q_proj, model.language_model.layers.54.self_attn.k_proj, model.language_model.layers.54.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.54.pre_feedforward_layernorm balance_layers: [model.language_model.layers.54.mlp.gate_proj, model.language_model.layers.54.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.54.mlp.up_proj balance_layers: [model.language_model.layers.54.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.55.input_layernorm balance_layers: [model.language_model.layers.55.self_attn.q_proj, model.language_model.layers.55.self_attn.k_proj, model.language_model.layers.55.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.55.pre_feedforward_layernorm balance_layers: [model.language_model.layers.55.mlp.gate_proj, model.language_model.layers.55.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.55.mlp.up_proj balance_layers: [model.language_model.layers.55.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.56.input_layernorm balance_layers: [model.language_model.layers.56.self_attn.q_proj, model.language_model.layers.56.self_attn.k_proj, model.language_model.layers.56.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.56.pre_feedforward_layernorm balance_layers: [model.language_model.layers.56.mlp.gate_proj, model.language_model.layers.56.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.56.mlp.up_proj balance_layers: [model.language_model.layers.56.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.57.input_layernorm balance_layers: [model.language_model.layers.57.self_attn.q_proj, model.language_model.layers.57.self_attn.k_proj, model.language_model.layers.57.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.57.pre_feedforward_layernorm balance_layers: [model.language_model.layers.57.mlp.gate_proj, model.language_model.layers.57.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.57.mlp.up_proj balance_layers: [model.language_model.layers.57.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.58.input_layernorm balance_layers: [model.language_model.layers.58.self_attn.q_proj, model.language_model.layers.58.self_attn.k_proj, model.language_model.layers.58.self_attn.v_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.58.pre_feedforward_layernorm balance_layers: [model.language_model.layers.58.mlp.gate_proj, model.language_model.layers.58.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.58.mlp.up_proj balance_layers: [model.language_model.layers.58.mlp.down_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.59.pre_feedforward_layernorm balance_layers: [model.language_model.layers.59.mlp.gate_proj, model.language_model.layers.59.mlp.up_proj] activation_hook_target: null - smooth_layer: model.language_model.layers.59.mlp.up_proj balance_layers: [model.language_model.layers.59.mlp.down_proj] activation_hook_target: null offload_device: cpu duo_scaling: true n_grid: 20