runtime error

Exit code: 1. Reason: :00<?, ?B/s] text.py: 100%|██████████| 6.85k/6.85k [00:00<00:00, 37.3MB/s] rope.py: 0%| | 0.00/1.57k [00:00<?, ?B/s] rope.py: 100%|██████████| 1.57k/1.57k [00:00<00:00, 10.8MB/s] utils.py: 0%| | 0.00/1.42k [00:00<?, ?B/s] utils.py: 100%|██████████| 1.42k/1.42k [00:00<00:00, 10.3MB/s] moondream.py: 0%| | 0.00/35.5k [00:00<?, ?B/s] moondream.py: 100%|██████████| 35.5k/35.5k [00:00<00:00, 77.6MB/s] lora.py: 0%| | 0.00/2.30k [00:00<?, ?B/s] lora.py: 100%|██████████| 2.30k/2.30k [00:00<00:00, 9.44MB/s] region.py: 0%| | 0.00/4.54k [00:00<?, ?B/s] region.py: 100%|██████████| 4.54k/4.54k [00:00<00:00, 28.0MB/s] `torch_dtype` is deprecated! Use `dtype` instead! Traceback (most recent call last): File "/app/app.py", line 9, in <module> model = AutoModelForCausalLM.from_pretrained( model_id, revision=revision, trust_remote_code=True, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, device_map="auto" ) File "/usr/local/lib/python3.13/site-packages/transformers/models/auto/auto_factory.py", line 597, in from_pretrained return model_class.from_pretrained( ~~~~~~~~~~~~~~~~~~~~~~~~~~~^ pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/transformers/modeling_utils.py", line 277, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4806, in from_pretrained raise ValueError( ...<2 lines>... ) ValueError: Using a `device_map`, `tp_plan`, `torch.device` context manager or setting `torch.set_default_device(device)` requires `accelerate`. You can install it with `pip install accelerate`

Container logs: