| { |
| "auto_mapping": null, |
| "base_model_name_or_path": "/mnt/workspace/workgroup/ustc/Bunny-v1/", |
| "bias": "none", |
| "fan_in_fan_out": false, |
| "inference_mode": true, |
| "init_lora_weights": true, |
| "layers_pattern": null, |
| "layers_to_transform": null, |
| "lora_alpha": 256, |
| "lora_dropout": 0.05, |
| "modules_to_save": null, |
| "peft_type": "LORA", |
| "r": 128, |
| "revision": null, |
| "target_modules": [ |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj", |
| "model.layers.4.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1", |
| "model.layers.22.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1", |
| "model.layers.20.mlp.fc1", |
| "model.layers.27.self_attn.k_proj", |
| "model.layers.2.mlp.fc2", |
| "model.layers.17.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1", |
| "model.layers.31.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj", |
| "model.layers.23.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1", |
| "model.layers.14.self_attn.dense", |
| "model.layers.31.mlp.fc2", |
| "model.layers.1.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj", |
| "model.layers.21.self_attn.v_proj", |
| "model.layers.26.mlp.fc1", |
| "model.layers.0.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj", |
| "model.layers.15.self_attn.v_proj", |
| "model.layers.1.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj", |
| "model.layers.11.mlp.fc2", |
| "model.layers.9.mlp.fc2", |
| "model.layers.3.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj", |
| "model.layers.3.mlp.fc2", |
| "model.layers.19.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1", |
| "model.layers.28.self_attn.v_proj", |
| "model.layers.11.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj", |
| "model.layers.6.self_attn.q_proj", |
| "model.layers.8.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj", |
| "model.layers.15.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2", |
| "model.layers.20.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1", |
| "model.layers.21.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj", |
| "model.layers.28.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj", |
| "model.layers.17.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj", |
| "model.layers.7.self_attn.q_proj", |
| "model.layers.30.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj", |
| "model.layers.0.self_attn.q_proj", |
| "model.layers.24.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj", |
| "model.layers.20.mlp.fc2", |
| "model.layers.8.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2", |
| "model.layers.6.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj", |
| "model.layers.11.self_attn.q_proj", |
| "model.layers.31.mlp.fc1", |
| "model.layers.1.mlp.fc1", |
| "model.layers.28.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj", |
| "model.layers.12.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj", |
| "model.layers.13.self_attn.v_proj", |
| "model.layers.24.mlp.fc2", |
| "model.layers.18.self_attn.v_proj", |
| "model.layers.3.mlp.fc1", |
| "model.layers.29.self_attn.q_proj", |
| "model.layers.23.self_attn.q_proj", |
| "model.layers.31.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj", |
| "model.layers.14.mlp.fc2", |
| "model.layers.26.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2", |
| "model.layers.12.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj", |
| "model.layers.10.mlp.fc1", |
| "model.layers.12.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj", |
| "model.layers.23.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1", |
| "model.layers.27.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj", |
| "model.layers.18.self_attn.dense", |
| "model.layers.28.mlp.fc2", |
| "model.layers.19.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj", |
| "model.layers.5.self_attn.q_proj", |
| "model.layers.3.self_attn.dense", |
| "model.layers.24.mlp.fc1", |
| "model.layers.6.self_attn.k_proj", |
| "model.layers.27.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1", |
| "model.layers.25.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj", |
| "model.layers.10.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj", |
| "model.layers.4.self_attn.k_proj", |
| "model.layers.13.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj", |
| "model.layers.4.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj", |
| "model.layers.16.mlp.fc1", |
| "model.layers.30.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1", |
| "model.layers.22.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2", |
| "model.layers.21.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2", |
| "model.layers.15.self_attn.k_proj", |
| "model.layers.8.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj", |
| "model.layers.14.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1", |
| "model.layers.30.mlp.fc2", |
| "model.layers.22.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj", |
| "model.layers.22.self_attn.k_proj", |
| "model.layers.19.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2", |
| "model.layers.14.mlp.fc1", |
| "model.layers.10.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2", |
| "model.layers.7.mlp.fc2", |
| "model.layers.23.mlp.fc1", |
| "model.layers.7.self_attn.k_proj", |
| "model.layers.13.self_attn.dense", |
| "model.layers.15.mlp.fc2", |
| "model.layers.15.self_attn.dense", |
| "model.layers.2.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj", |
| "model.layers.24.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2", |
| "model.layers.17.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj", |
| "model.layers.28.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj", |
| "model.layers.22.self_attn.v_proj", |
| "model.layers.29.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2", |
| "model.layers.30.mlp.fc1", |
| "model.layers.29.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj", |
| "model.layers.5.self_attn.dense", |
| "model.layers.20.self_attn.dense", |
| "model.layers.12.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj", |
| "model.layers.6.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj", |
| "model.layers.20.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1", |
| "model.layers.3.self_attn.q_proj", |
| "model.layers.29.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj", |
| "model.layers.30.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1", |
| "model.layers.8.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj", |
| "model.layers.9.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj", |
| "model.layers.27.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2", |
| "model.layers.13.self_attn.k_proj", |
| "model.layers.26.mlp.fc2", |
| "model.layers.9.self_attn.dense", |
| "model.layers.1.self_attn.q_proj", |
| "model.layers.10.self_attn.dense", |
| "model.layers.14.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2", |
| "model.layers.12.mlp.fc1", |
| "model.layers.13.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj", |
| "model.layers.26.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj", |
| "model.layers.4.mlp.fc1", |
| "model.layers.18.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj", |
| "model.layers.31.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2", |
| "model.layers.24.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2", |
| "model.layers.16.self_attn.dense", |
| "model.layers.25.self_attn.k_proj", |
| "model.layers.0.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj", |
| "model.layers.5.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2", |
| "model.layers.27.mlp.fc2", |
| "model.layers.23.self_attn.v_proj", |
| "model.layers.16.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj", |
| "model.layers.11.mlp.fc1", |
| "model.layers.9.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1", |
| "model.layers.11.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj", |
| "model.layers.6.self_attn.dense", |
| "model.layers.4.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1", |
| "model.layers.18.self_attn.k_proj", |
| "model.layers.7.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2", |
| "model.layers.22.self_attn.q_proj", |
| "model.layers.29.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj", |
| "model.layers.2.self_attn.q_proj", |
| "model.layers.17.self_attn.v_proj", |
| "model.layers.1.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj", |
| "model.layers.16.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1", |
| "model.layers.0.mlp.fc1", |
| "model.layers.5.mlp.fc2", |
| "model.layers.8.self_attn.dense", |
| "model.layers.21.self_attn.k_proj", |
| "model.layers.29.mlp.fc1", |
| "model.layers.9.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj", |
| "model.layers.5.self_attn.k_proj", |
| "model.layers.30.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1", |
| "model.layers.2.self_attn.v_proj", |
| "model.layers.3.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1", |
| "model.layers.19.self_attn.v_proj", |
| "model.layers.15.self_attn.q_proj", |
| "model.layers.6.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj", |
| "model.layers.8.self_attn.v_proj", |
| "model.layers.28.self_attn.dense", |
| "model.layers.10.self_attn.v_proj", |
| "model.layers.21.mlp.fc2", |
| "model.layers.13.mlp.fc2", |
| "model.layers.10.mlp.fc2", |
| "model.layers.7.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj", |
| "model.layers.25.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj", |
| "model.layers.11.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj", |
| "model.layers.17.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2", |
| "model.layers.2.self_attn.k_proj", |
| "model.layers.4.mlp.fc2", |
| "model.layers.21.self_attn.dense", |
| "model.layers.16.mlp.fc2", |
| "model.layers.18.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj", |
| "model.layers.23.self_attn.dense", |
| "model.layers.12.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj", |
| "model.layers.0.mlp.fc2", |
| "model.layers.25.self_attn.dense", |
| "model.layers.25.mlp.fc1", |
| "model.layers.27.mlp.fc1", |
| "model.layers.18.mlp.fc1", |
| "model.layers.24.self_attn.q_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2", |
| "model.layers.7.self_attn.dense", |
| "model.layers.25.mlp.fc2", |
| "model.layers.19.self_attn.dense", |
| "model.layers.16.self_attn.q_proj", |
| "model.layers.17.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj", |
| "model.layers.26.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj", |
| "model.layers.26.self_attn.k_proj", |
| "model.layers.1.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj", |
| "model.layers.0.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj", |
| "model.layers.20.self_attn.k_proj", |
| "model.layers.2.mlp.fc1", |
| "model.layers.9.self_attn.v_proj", |
| "model.layers.5.self_attn.v_proj", |
| "model.layers.14.self_attn.v_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj", |
| "model.layers.19.mlp.fc2", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj", |
| "model.layers.31.self_attn.dense", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj", |
| "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj" |
| ], |
| "task_type": "CAUSAL_LM" |
| } |
