runtime error

Exit code: 1. Reason: 0:12<00:45, 63.4MB/s] model-00002-of-00002.safetensors: 21%|██ | 731M/3.50G [00:13<00:40, 69.0MB/s] model-00002-of-00002.safetensors: 29%|██▉ | 1.03G/3.50G [00:14<00:20, 120MB/s] model-00002-of-00002.safetensors: 34%|███▍ | 1.21G/3.50G [00:16<00:18, 124MB/s] model-00002-of-00002.safetensors: 41%|████ | 1.44G/3.50G [00:17<00:14, 142MB/s] model-00002-of-00002.safetensors: 47%|████▋ | 1.65G/3.50G [00:18<00:11, 158MB/s] model-00002-of-00002.safetensors: 52%|█████▏ | 1.83G/3.50G [00:19<00:11, 142MB/s] model-00002-of-00002.safetensors: 60%|█████▉ | 2.09G/3.50G [00:21<00:08, 167MB/s] model-00002-of-00002.safetensors: 65%|██████▍ | 2.27G/3.50G [00:22<00:07, 157MB/s] model-00002-of-00002.safetensors: 77%|███████▋ | 2.70G/3.50G [00:23<00:03, 219MB/s] model-00002-of-00002.safetensors: 91%|█████████ | 3.19G/3.50G [00:24<00:01, 284MB/s] model-00002-of-00002.safetensors: 100%|██████████| 3.50G/3.50G [00:25<00:00, 138MB/s] Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 5.76it/s] generation_config.json: 0%| | 0.00/116 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 116/116 [00:00<00:00, 764kB/s] Some parameters are on the meta device because they were offloaded to the cpu and disk. You shouldn't move a model that is dispatched using accelerate hooks. Traceback (most recent call last): File "/home/user/app/app.py", line 16, in <module> ).to("cuda" if torch.cuda.is_available() else "cpu") File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 462, in wrapper raise RuntimeError("You can't move a model that has some modules offloaded to cpu or disk.") RuntimeError: You can't move a model that has some modules offloaded to cpu or disk.

Container logs: