runtime error

Exit code: 1. Reason: [A model-00003-of-00003.safetensors: 2%|▏ | 96.0M/4.55G [00:05<03:32, 20.9MB/s] model-00003-of-00003.safetensors: 3%|▎ | 144M/4.55G [00:07<03:02, 24.1MB/s]  model-00003-of-00003.safetensors: 7%|▋ | 316M/4.55G [00:09<01:31, 46.5MB/s] model-00003-of-00003.safetensors: 25%|██▍ | 1.12G/4.55G [00:10<00:16, 206MB/s] model-00003-of-00003.safetensors: 41%|████ | 1.86G/4.55G [00:11<00:08, 328MB/s] model-00003-of-00003.safetensors: 51%|█████▏ | 2.33G/4.55G [00:12<00:06, 351MB/s] model-00003-of-00003.safetensors: 90%|████████▉ | 4.08G/4.55G [00:13<00:00, 702MB/s] model-00003-of-00003.safetensors: 100%|██████████| 4.55G/4.55G [00:14<00:00, 320MB/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 100%|██████████| 3/3 [00:00<00:00, 38.01it/s] generation_config.json: 0%| | 0.00/116 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 116/116 [00:00<00:00, 911kB/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 "/app/app.py", line 274, in <module> preloaded_output = get_preload_output() File "/app/app.py", line 269, in get_preload_output html_output = extract_and_visualize(abstract) File "/app/app.py", line 141, in extract_and_visualize raw_output = run_mistral_extract(sentence) File "/app/app.py", line 81, in run_mistral_extract tokenizer, model, device = get_model() File "/app/app.py", line 75, in get_model model.to(device) 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: