runtime error

Exit code: 1. Reason: .15k [00:00<00:00, 7.16MB/s] model.safetensors: 0%| | 0.00/4.42G [00:00<?, ?B/s] model.safetensors: 0%| | 542k/4.42G [00:01<2:26:41, 502kB/s] model.safetensors: 2%|▏ | 70.8M/4.42G [00:02<01:48, 40.1MB/s] model.safetensors: 5%|▍ | 205M/4.42G [00:04<01:27, 47.9MB/s]  model.safetensors: 8%|▊ | 339M/4.42G [00:05<00:58, 69.7MB/s] model.safetensors: 14%|█▎ | 607M/4.42G [00:06<00:31, 121MB/s]  model.safetensors: 18%|█▊ | 808M/4.42G [00:08<00:28, 127MB/s] model.safetensors: 23%|██▎ | 1.01G/4.42G [00:11<00:39, 86.5MB/s] model.safetensors: 33%|███▎ | 1.48G/4.42G [00:13<00:19, 154MB/s]  model.safetensors: 44%|████▍ | 1.94G/4.42G [00:14<00:11, 215MB/s] model.safetensors: 59%|█████▉ | 2.61G/4.42G [00:15<00:05, 312MB/s] model.safetensors: 73%|███████▎ | 3.21G/4.42G [00:16<00:03, 368MB/s] model.safetensors: 86%|████████▋ | 3.81G/4.42G [00:17<00:01, 418MB/s] model.safetensors: 100%|██████████| 4.42G/4.42G [00:18<00:00, 242MB/s] `Qwen2VLRotaryEmbedding` can now be fully parameterized by passing the model config through the `config` argument. All other arguments will be removed in v4.46 generation_config.json: 0%| | 0.00/261 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 261/261 [00:00<00:00, 1.68MB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 8, in <module> model = Qwen2VLForConditionalGeneration.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4302, in from_pretrained dispatch_model(model, **device_map_kwargs) File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 504, in dispatch_model raise ValueError( ValueError: You are trying to offload the whole model to the disk. Please use the `disk_offload` function instead.

Container logs: