runtime error

Exit code: 1. Reason: ir own `video_preprocessor.json` file. You can rename the file or load and save the processor back which renames it automatically. Loading from `preprocessor.json` will be removed in v5.0. chat_template.json: 0%| | 0.00/1.05k [00:00<?, ?B/s] chat_template.json: 100%|██████████| 1.05k/1.05k [00:00<00:00, 5.65MB/s] Loading and applying adapter... adapter_config.json: 0%| | 0.00/810 [00:00<?, ?B/s] adapter_config.json: 100%|██████████| 810/810 [00:00<00:00, 4.54MB/s] The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers and GPU quantization are unavailable. adapter_model.safetensors: 0%| | 0.00/59.0M [00:00<?, ?B/s] adapter_model.safetensors: 100%|██████████| 59.0M/59.0M [00:01<00:00, 51.2MB/s] adapter_model.safetensors: 100%|██████████| 59.0M/59.0M [00:01<00:00, 51.1MB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 33, in <module> model = PeftModel.from_pretrained(model, adapter_id) File "/usr/local/lib/python3.10/site-packages/peft/peft_model.py", line 555, in from_pretrained load_result = model.load_adapter( File "/usr/local/lib/python3.10/site-packages/peft/peft_model.py", line 1385, in load_adapter dispatch_model( File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 383, in dispatch_model raise ValueError( ValueError: We need an `offload_dir` to dispatch this model according to this `device_map`, the following submodules need to be offloaded: base_model.model.model.language_model.layers.29, base_model.model.model.language_model.layers.30, base_model.model.model.language_model.layers.31, base_model.model.model.language_model.layers.32, base_model.model.model.language_model.layers.33, base_model.model.model.language_model.layers.34, base_model.model.model.language_model.layers.35, base_model.model.model.language_model.norm, base_model.model.model.language_model.rotary_emb.

Container logs: