runtime error

Exit code: 1. Reason: 44%|████▍ | 1.95G/4.39G [00:06<00:07, 320MB/s] transformer/diffusion_pytorch_model-0000(…): 56%|█████▌ | 2.46G/4.39G [00:07<00:05, 375MB/s] transformer/diffusion_pytorch_model-0000(…): 75%|███████▌ | 3.31G/4.39G [00:09<00:02, 479MB/s] transformer/diffusion_pytorch_model-0000(…): 88%|████████▊ | 3.86G/4.39G [00:10<00:01, 439MB/s] transformer/diffusion_pytorch_model-0000(…): 99%|█████████▉| 4.34G/4.39G [00:11<00:00, 421MB/s] transformer/diffusion_pytorch_model-0000(…): 100%|██████████| 4.39G/4.39G [00:11<00:00, 368MB/s] Traceback (most recent call last): File "/app/app.py", line 97, in <module> transformer=QwenImageTransformer2DModel.from_pretrained( ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^ "linoyts/Qwen-Image-Edit-Rapid-AIO", ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ...<2 lines>... device_map="auto" # Здесь 'auto' работает нормально (для трансформера) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ), ^ File "/usr/local/lib/python3.13/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/usr/local/lib/python3.13/site-packages/diffusers/models/modeling_utils.py", line 1416, in from_pretrained ) = cls._load_pretrained_model( ~~~~~~~~~~~~~~~~~~~~~~~~~~^ model, ^^^^^^ ...<14 lines>... disable_mmap=disable_mmap, ^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/diffusers/models/modeling_utils.py", line 1745, in _load_pretrained_model raise ValueError( ...<3 lines>... ) ValueError: The current `device_map` had weights offloaded to the disk. Please provide an `offload_folder` for them. Alternatively, make sure you have `safetensors` installed if the model you are using offers the weights in this format.

Container logs: