runtime error

Exit code: 1. Reason: heckpoint shards: 50%|█████ | 2/4 [00:31<00:31, 15.81s/it] Loading checkpoint shards: 50%|█████ | 2/4 [00:36<00:36, 18.02s/it] Traceback (most recent call last): File "/app/app.py", line 96, in <module> transformer=QwenImageTransformer2DModel.from_pretrained( File "/root/.pyenv/versions/3.10.19/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/root/.pyenv/versions/3.10.19/lib/python3.10/site-packages/diffusers/models/modeling_utils.py", line 1296, in from_pretrained ) = cls._load_pretrained_model( File "/root/.pyenv/versions/3.10.19/lib/python3.10/site-packages/diffusers/models/modeling_utils.py", line 1678, in _load_pretrained_model offload_index, state_dict_index, _mismatched_keys, _error_msgs = load_fn(shard_file) File "/root/.pyenv/versions/3.10.19/lib/python3.10/site-packages/diffusers/models/model_loading_utils.py", line 367, in _load_shard_file offload_index, state_dict_index = load_model_dict_into_meta( File "/root/.pyenv/versions/3.10.19/lib/python3.10/site-packages/diffusers/models/model_loading_utils.py", line 307, in load_model_dict_into_meta set_module_tensor_to_device(model, param_name, param_device, value=param, **set_module_kwargs) File "/root/.pyenv/versions/3.10.19/lib/python3.10/site-packages/accelerate/utils/modeling.py", line 343, in set_module_tensor_to_device new_value = value.to(device, non_blocking=non_blocking) torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 72.00 MiB. GPU 0 has a total capacity of 22.30 GiB of which 10.69 MiB is free. Process 18242 has 22.29 GiB memory in use. Of the allocated memory 22.03 GiB is allocated by PyTorch, and 7.53 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)

Container logs: