runtime error

Exit code: 1. Reason: �██| 315/315 [00:00<00:00, 1.64MB/s] Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. chat_template.jinja: 0%| | 0.00/7.30k [00:00<?, ?B/s] chat_template.jinja: 100%|██████████| 7.30k/7.30k [00:00<00:00, 29.4MB/s] config.json: 0%| | 0.00/2.38k [00:00<?, ?B/s] config.json: 100%|██████████| 2.38k/2.38k [00:00<00:00, 16.5MB/s] tokenizer_config.json: 0%| | 0.00/9.00k [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 9.00k/9.00k [00:00<00:00, 38.1MB/s] tokenizer.json: 0%| | 0.00/20.0M [00:00<?, ?B/s] tokenizer.json: 100%|██████████| 20.0M/20.0M [00:00<00:00, 32.0MB/s] [transformers] `torch_dtype` is deprecated! Use `dtype` instead! Traceback (most recent call last): File "/app/app.py", line 17, in <module> model = AutoModelForImageTextToText.from_pretrained( model_id, ...<2 lines>... device_map="cuda" ) File "/usr/local/lib/python3.13/site-packages/transformers/models/auto/auto_factory.py", line 405, 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 4089, in from_pretrained device_map = check_and_set_device_map(device_map) # warn, error and fix the device map File "/usr/local/lib/python3.13/site-packages/transformers/integrations/accelerate.py", line 134, in check_and_set_device_map 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: