| { |
| "alpha_pattern": {}, |
| "auto_mapping": null, |
| "base_model_name_or_path": "togethercomputer/gemma-3-4b-it-VLM", |
| "bias": "none", |
| "corda_config": null, |
| "eva_config": null, |
| "exclude_modules": [ |
| "model.vision_tower.encoder.layers.21.mlp", |
| "model.vision_tower.encoder.layers.16.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.24.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.20.layer_norm1", |
| "model.vision_tower.encoder.layers.1.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.22.mlp.fc2", |
| "model.vision_tower.embeddings.patch_embedding", |
| "model.vision_tower.encoder.layers.26.mlp", |
| "model.vision_tower.encoder.layers.23.mlp.fc1", |
| "model.vision_tower.encoder.layers.8.layer_norm1", |
| "model.vision_tower.encoder.layers.5.self_attn", |
| "model.vision_tower.encoder.layers.17.mlp", |
| "model.vision_tower.encoder.layers.22", |
| "model.vision_tower.encoder.layers.15.self_attn", |
| "model.vision_tower.encoder.layers.15.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.11.mlp.fc1", |
| "model.vision_tower.encoder.layers.18.mlp.fc2", |
| "model.vision_tower.encoder.layers.9.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.24.layer_norm1", |
| "model.vision_tower.encoder.layers.6.mlp.fc1", |
| "model.vision_tower.encoder.layers.11.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.19.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.17.mlp.fc2", |
| "model.vision_tower.encoder.layers.21.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.0.layer_norm1", |
| "model.vision_tower.encoder.layers.8.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.22.mlp", |
| "model.vision_tower.encoder.layers.4.layer_norm1", |
| "model.vision_tower.encoder.layers.21.layer_norm1", |
| "model.vision_tower.encoder.layers.0.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.0.mlp.fc1", |
| "model.vision_tower.encoder.layers.10.mlp.fc2", |
| "model.vision_tower.encoder.layers.7.mlp", |
| "model.vision_tower.encoder.layers.6.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.8.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.2.layer_norm2", |
| "model.vision_tower.encoder.layers", |
| "model.vision_tower.encoder.layers.18.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.3.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.26.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.24.mlp.fc1", |
| "model.vision_tower.encoder.layers.18.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.13.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.17.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.1.self_attn", |
| "model.vision_tower.encoder.layers.6.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.12.mlp.fc1", |
| "model.vision_tower.encoder.layers.20.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.9.layer_norm1", |
| "model.vision_tower.encoder.layers.10", |
| "model.vision_tower.encoder.layers.4.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.3", |
| "model.vision_tower.encoder.layers.12", |
| "model.vision_tower.encoder.layers.21.mlp.activation_fn", |
| "model.multi_modal_projector.mm_soft_emb_norm", |
| "model.vision_tower.encoder.layers.13.mlp", |
| "model.vision_tower.embeddings", |
| "model.vision_tower.encoder.layers.13.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.2.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.5.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.19.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.25.layer_norm2", |
| "model.vision_tower.encoder.layers.4.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.9.self_attn", |
| "model.vision_tower.encoder.layers.3.mlp.fc1", |
| "model.vision_tower.encoder.layers.14", |
| "model.vision_tower.encoder.layers.15.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.9.mlp.fc2", |
| "model.vision_tower.encoder.layers.2.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.7.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.0.self_attn", |
| "model.vision_tower.encoder.layers.18.mlp.fc1", |
| "model.vision_tower.encoder.layers.11", |
| "model.vision_tower.encoder.layers.8.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.26", |
| "model.vision_tower.encoder.layers.12.self_attn.k_proj", |
| "model.vision_tower.encoder", |
| "model.vision_tower.encoder.layers.2.mlp.fc1", |
| "model.vision_tower.encoder.layers.3.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.19.mlp.fc1", |
| "model.vision_tower.encoder.layers.21.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.5.layer_norm2", |
| "model.vision_tower.encoder.layers.14.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.9.mlp.fc1", |
| "model.vision_tower.encoder.layers.13.layer_norm2", |
| "model.vision_tower.encoder.layers.20.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.11.layer_norm2", |
| "model.vision_tower.encoder.layers.23.layer_norm1", |
| "model.vision_tower.encoder.layers.0.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.26.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.22.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.15", |
| "model.vision_tower.encoder.layers.16", |
| "model.vision_tower.encoder.layers.16.mlp", |
| "model.vision_tower.encoder.layers.26.layer_norm2", |
| "model.vision_tower.encoder.layers.9", |
| "model.vision_tower.encoder.layers.16.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.14.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.6", |
| "model.vision_tower.encoder.layers.20.layer_norm2", |
| "model.vision_tower.encoder.layers.6.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.3.mlp.fc2", |
| "model.vision_tower.encoder.layers.1.layer_norm1", |
| "model.vision_tower.encoder.layers.13.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.9.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.21.mlp.fc2", |
| "model.vision_tower.encoder.layers.8", |
| "model.vision_tower.encoder.layers.19", |
| "model.vision_tower.encoder.layers.5.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.24.mlp.fc2", |
| "model.vision_tower.encoder.layers.24.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.6.layer_norm2", |
| "model.vision_tower.encoder.layers.2.mlp", |
| "model.vision_tower.encoder.layers.11.mlp.fc2", |
| "model.vision_tower.encoder.layers.4.mlp", |
| "model.vision_tower.encoder.layers.12.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.10.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.15.mlp.fc2", |
| "model.vision_tower.encoder.layers.26.mlp.fc2", |
| "model.vision_tower.encoder.layers.19.layer_norm1", |
| "model.vision_tower.encoder.layers.16.layer_norm2", |
| "model.vision_tower.encoder.layers.26.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.21", |
| "model.vision_tower.encoder.layers.3.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.8.mlp.fc2", |
| "model.vision_tower.encoder.layers.15.layer_norm2", |
| "model.vision_tower.encoder.layers.16.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.16.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.13.mlp.fc2", |
| "model.vision_tower.encoder.layers.22.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.2.self_attn", |
| "model.vision_tower.encoder.layers.21.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.14.self_attn", |
| "model.vision_tower.encoder.layers.17.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.20.mlp.fc1", |
| "model.vision_tower.encoder.layers.4.mlp.fc1", |
| "model.vision_tower.encoder.layers.5.mlp.fc2", |
| "model.vision_tower.encoder.layers.12.mlp.fc2", |
| "model.vision_tower.encoder.layers.4.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.10.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.25.mlp.fc2", |
| "model.vision_tower.encoder.layers.0.mlp", |
| "model.vision_tower.encoder.layers.10.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.12.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.17.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.13.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.12.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.15.layer_norm1", |
| "model.vision_tower.encoder.layers.24.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.11.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.3.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.12.layer_norm1", |
| "model.vision_tower.encoder.layers.22.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.14.layer_norm2", |
| "model.vision_tower.encoder.layers.26.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.1.mlp", |
| "model.vision_tower.encoder.layers.2.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.25.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.9.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.22.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.18.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.18.layer_norm1", |
| "model.vision_tower.encoder.layers.14.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.24.self_attn", |
| "model.vision_tower.encoder.layers.13.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.7.mlp.activation_fn", |
| "model.vision_tower.embeddings.position_embedding", |
| "model.vision_tower.encoder.layers.0.layer_norm2", |
| "model.vision_tower.encoder.layers.3.layer_norm1", |
| "model.vision_tower.encoder.layers.0.mlp.fc2", |
| "model.vision_tower.encoder.layers.5.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.9.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.17.layer_norm2", |
| "model.vision_tower.encoder.layers.17.mlp.fc1", |
| "model.multi_modal_projector.avg_pool", |
| "model.vision_tower.encoder.layers.5.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.16.mlp.fc1", |
| "model.vision_tower.encoder.layers.23.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.6.layer_norm1", |
| "model.vision_tower.encoder.layers.2.layer_norm1", |
| "model.vision_tower.encoder.layers.18.self_attn", |
| "model.vision_tower.encoder.layers.19.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.8.self_attn", |
| "model.vision_tower.encoder.layers.23.mlp", |
| "model.vision_tower.encoder.layers.4.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.25.mlp.fc1", |
| "model.vision_tower.encoder.layers.7.mlp.fc1", |
| "model.vision_tower.encoder.layers.17.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.14.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.1.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.1.mlp.fc2", |
| "model.vision_tower.encoder.layers.26.self_attn", |
| "model.vision_tower.encoder.layers.3.layer_norm2", |
| "model.vision_tower.encoder.layers.20.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.0", |
| "model.vision_tower.encoder.layers.1.layer_norm2", |
| "model.vision_tower.encoder.layers.4", |
| "model.vision_tower.encoder.layers.10.mlp.fc1", |
| "model.vision_tower.encoder.layers.7.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.26.mlp.fc1", |
| "model.vision_tower.encoder.layers.7.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.7.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.22.layer_norm2", |
| "model.vision_tower.encoder.layers.5.mlp", |
| "model.vision_tower.encoder.layers.5", |
| "model.vision_tower.encoder.layers.25.mlp", |
| "model.vision_tower.encoder.layers.14.mlp.fc1", |
| "model.vision_tower.encoder.layers.22.self_attn", |
| "model.vision_tower.encoder.layers.8.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.21.layer_norm2", |
| "model.vision_tower.encoder.layers.6.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.23.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.25", |
| "model.vision_tower.encoder.layers.12.layer_norm2", |
| "model.vision_tower.encoder.layers.4.self_attn", |
| "model.vision_tower.encoder.layers.24", |
| "model.vision_tower.encoder.layers.20.mlp.fc2", |
| "model.vision_tower.post_layernorm", |
| "model.vision_tower.encoder.layers.13.mlp.fc1", |
| "model.vision_tower.encoder.layers.1.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.25.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.19.mlp.fc2", |
| "model.vision_tower.encoder.layers.19.self_attn", |
| "model.vision_tower.encoder.layers.2", |
| "model.vision_tower.encoder.layers.23.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.26.layer_norm1", |
| "model.vision_tower.encoder.layers.15.mlp.fc1", |
| "model.vision_tower.encoder.layers.18.layer_norm2", |
| "model.vision_tower.encoder.layers.10.mlp", |
| "model.vision_tower.encoder.layers.17.layer_norm1", |
| "model.vision_tower.encoder.layers.23.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.14.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.10.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.19.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.21.self_attn", |
| "model.vision_tower.encoder.layers.12.self_attn", |
| "model.vision_tower.encoder.layers.14.mlp.fc2", |
| "model.vision_tower.encoder.layers.9.layer_norm2", |
| "model.vision_tower.encoder.layers.12.mlp", |
| "model.vision_tower.encoder.layers.17.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.17.self_attn", |
| "model.vision_tower.encoder.layers.24.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.19.mlp", |
| "model.vision_tower.encoder.layers.22.layer_norm1", |
| "model.vision_tower.encoder.layers.16.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.22.mlp.fc1", |
| "model.vision_tower.encoder.layers.7.mlp.fc2", |
| "model.vision_tower.encoder.layers.14.layer_norm1", |
| "model.vision_tower.encoder.layers.20.self_attn", |
| "model.vision_tower.encoder.layers.11.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.6.mlp", |
| "model.vision_tower.encoder.layers.10.layer_norm2", |
| "model.vision_tower.encoder.layers.23.mlp.fc2", |
| "model.vision_tower.encoder.layers.3.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.20.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.16.layer_norm1", |
| "model.vision_tower.encoder.layers.24.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.23.self_attn", |
| "model.vision_tower.encoder.layers.11.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.6.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.13", |
| "model.vision_tower.encoder.layers.23", |
| "model.vision_tower.encoder.layers.0.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.11.self_attn", |
| "model.vision_tower.encoder.layers.2.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.22.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.20.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.18.mlp", |
| "model.vision_tower.encoder.layers.8.layer_norm2", |
| "model.vision_tower.encoder.layers.18", |
| "model.vision_tower.encoder.layers.1.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.9.mlp", |
| "model.vision_tower.encoder.layers.18.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.25.layer_norm1", |
| "model.vision_tower.encoder.layers.21.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.11.mlp", |
| "model.vision_tower.encoder.layers.26.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.8.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.20", |
| "model.vision_tower.encoder.layers.4.layer_norm2", |
| "model.vision_tower.encoder.layers.7.layer_norm2", |
| "model.vision_tower.encoder.layers.4.self_attn.k_proj", |
| "model.vision_tower", |
| "model.vision_tower.encoder.layers.1", |
| "model.vision_tower.encoder.layers.15.mlp", |
| "model.vision_tower.encoder.layers.14.mlp", |
| "model.vision_tower.encoder.layers.11.self_attn.v_proj", |
| "model.vision_tower.encoder.layers.25.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.6.mlp.fc2", |
| "model.vision_tower.encoder.layers.20.mlp", |
| "model.vision_tower.encoder.layers.10.layer_norm1", |
| "model.vision_tower.encoder.layers.5.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.6.self_attn", |
| "model.vision_tower.encoder.layers.16.self_attn", |
| "model.vision_tower.encoder.layers.17", |
| "model.vision_tower.encoder.layers.8.mlp.fc1", |
| "model.multi_modal_projector", |
| "model.vision_tower.encoder.layers.23.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.5.layer_norm1", |
| "model.vision_tower.encoder.layers.7.layer_norm1", |
| "model.vision_tower.encoder.layers.10.self_attn.out_proj", |
| "model.vision_tower.encoder.layers.1.mlp.fc1", |
| "model.vision_tower.encoder.layers.8.mlp", |
| "model.vision_tower.encoder.layers.21.mlp.fc1", |
| "model.vision_tower.encoder.layers.11.layer_norm1", |
| "model.vision_tower.encoder.layers.23.layer_norm2", |
| "model.vision_tower.encoder.layers.16.mlp.fc2", |
| "model.vision_tower.encoder.layers.25.self_attn.k_proj", |
| "model.vision_tower.encoder.layers.0.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.7.self_attn", |
| "model.vision_tower.encoder.layers.2.mlp.fc2", |
| "model.vision_tower.encoder.layers.9.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.12.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.13.self_attn", |
| "model.vision_tower.encoder.layers.0.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.24.layer_norm2", |
| "model.vision_tower.encoder.layers.19.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.2.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.15.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.19.layer_norm2", |
| "model.vision_tower.encoder.layers.24.mlp", |
| "model.vision_tower.encoder.layers.10.self_attn", |
| "model.vision_tower.encoder.layers.3.self_attn", |
| "model.vision_tower.encoder.layers.5.mlp.fc1", |
| "model.vision_tower.encoder.layers.18.mlp.activation_fn", |
| "model.vision_tower.encoder.layers.4.mlp.fc2", |
| "model.vision_tower.encoder.layers.25.self_attn", |
| "model.vision_tower.encoder.layers.25.self_attn.q_proj", |
| "model.vision_tower.encoder.layers.13.layer_norm1", |
| "model.vision_tower.encoder.layers.7", |
| "model.vision_tower.encoder.layers.3.mlp", |
| "model.vision_tower.encoder.layers.1.self_attn.out_proj" |
| ], |
| "fan_in_fan_out": false, |
| "inference_mode": true, |
| "init_lora_weights": true, |
| "layer_replication": null, |
| "layers_pattern": null, |
| "layers_to_transform": null, |
| "loftq_config": {}, |
| "lora_alpha": 128, |
| "lora_bias": false, |
| "lora_dropout": 0.05000000074505806, |
| "megatron_config": null, |
| "megatron_core": "megatron.core", |
| "modules_to_save": null, |
| "peft_type": "LORA", |
| "r": 64, |
| "rank_pattern": {}, |
| "revision": null, |
| "target_modules": [ |
| "q_proj", |
| "v_proj", |
| "o_proj", |
| "k_proj" |
| ], |
| "task_type": "CAUSAL_LM", |
| "trainable_token_indices": null, |
| "use_dora": false, |
| "use_rslora": false |
| } |
