| { |
| "alpha_pattern": {}, |
| "auto_mapping": null, |
| "base_model_name_or_path": "/shared/cycle2_bgu_azencot_prj/models/Qwen3-VL-8B-Instruct", |
| "bias": "none", |
| "corda_config": null, |
| "eva_config": null, |
| "exclude_modules": "(.*\\.visual\\..*|.*language_model\\..*)", |
| "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": 0.05, |
| "megatron_config": null, |
| "megatron_core": "megatron.core", |
| "modules_to_save": [ |
| "visual_dino.merger", |
| "visual_dino.deepstack_merger_list.0", |
| "visual_dino.deepstack_merger_list.1", |
| "visual_dino.deepstack_merger_list.2" |
| ], |
| "peft_type": "LORA", |
| "qalora_group_size": 16, |
| "r": 64, |
| "rank_pattern": {}, |
| "revision": null, |
| "target_modules": [ |
| "q_proj", |
| "up_proj", |
| "gate_proj", |
| "o_proj", |
| "k_proj", |
| "down_proj", |
| "v_proj" |
| ], |
| "task_type": "CAUSAL_LM", |
| "trainable_token_indices": null, |
| "use_dora": false, |
| "use_qalora": false, |
| "use_rslora": false |
| } |
