runtime error

Exit code: 1. Reason: Using device: cpu Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'mrope_section'} Downloading shards: 0%| | 0/5 [00:00<?, ?it/s] Downloading shards: 20%|██ | 1/5 [00:13<00:55, 13.88s/it] Downloading shards: 40%|████ | 2/5 [00:27<00:40, 13.57s/it] Downloading shards: 60%|██████ | 3/5 [00:42<00:28, 14.37s/it] Downloading shards: 80%|████████ | 4/5 [00:56<00:14, 14.22s/it] Downloading shards: 100%|██████████| 5/5 [01:02<00:00, 11.21s/it] Downloading shards: 100%|██████████| 5/5 [01:02<00:00, 12.48s/it] `Qwen2VLRotaryEmbedding` can now be fully parameterized by passing the model config through the `config` argument. All other arguments will be removed in v4.46 Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s] Loading checkpoint shards: 20%|██ | 1/5 [00:09<00:38, 9.69s/it] Loading checkpoint shards: 100%|██████████| 5/5 [00:09<00:00, 1.94s/it] Some parameters are on the meta device because they were offloaded to the disk and cpu. You shouldn't move a model that is dispatched using accelerate hooks. Traceback (most recent call last): File "/home/user/app/app.py", line 18, in <module> model.to(device) File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 456, 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: