runtime error

Exit code: 1. Reason: 01-of-00002.safetensors: 12%|█▏ | 612M/4.99G [00:05<00:32, 134MB/s]  model-00001-of-00002.safetensors: 38%|███▊ | 1.88G/4.99G [00:06<00:07, 440MB/s] model-00001-of-00002.safetensors: 57%|█████▋ | 2.82G/4.99G [00:07<00:03, 575MB/s] model-00001-of-00002.safetensors: 71%|███████ | 3.52G/4.99G [00:09<00:02, 568MB/s] model-00001-of-00002.safetensors: 84%|████████▍ | 4.19G/4.99G [00:10<00:01, 590MB/s] model-00001-of-00002.safetensors: 100%|██████████| 4.99G/4.99G [00:10<00:00, 463MB/s] model-00002-of-00002.safetensors: 0%| | 0.00/241M [00:00<?, ?B/s] model-00002-of-00002.safetensors: 44%|████▍ | 107M/241M [00:01<00:01, 95.9MB/s] model-00002-of-00002.safetensors: 100%|██████████| 241M/241M [00:01<00:00, 164MB/s] Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:03<00:03, 3.23s/it] Loading checkpoint shards: 100%|██████████| 2/2 [00:03<00:00, 1.62s/it] generation_config.json: 0%| | 0.00/187 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 187/187 [00:00<00:00, 1.47MB/s] 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 135, in <module> launch_app() File "/home/user/app/app.py", line 86, in launch_app model = AutoModelForCausalLM.from_pretrained(model_name, device_map='auto', token=hf_token).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: