runtime error

Exit code: 1. Reason: in from_pretrained ) = cls._load_pretrained_model( ~~~~~~~~~~~~~~~~~~~~~~~~~~^ model, ^^^^^^ ...<14 lines>... disable_mmap=disable_mmap, ^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/root/.pyenv/versions/3.13.11/lib/python3.13/site-packages/diffusers/models/modeling_utils.py", line 1701, in _load_pretrained_model offload_index, state_dict_index, _mismatched_keys, _error_msgs = load_fn(shard_file) ~~~~~~~^^^^^^^^^^^^ File "/root/.pyenv/versions/3.13.11/lib/python3.13/site-packages/diffusers/models/model_loading_utils.py", line 369, in _load_shard_file offload_index, state_dict_index = load_model_dict_into_meta( ~~~~~~~~~~~~~~~~~~~~~~~~~^ model, ^^^^^^ ...<9 lines>... state_dict_folder=state_dict_folder, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ) ^ File "/root/.pyenv/versions/3.13.11/lib/python3.13/site-packages/diffusers/models/model_loading_utils.py", line 308, 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/3.13.11/lib/python3.13/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 28.69 MiB is free. Process 39957 has 22.27 GiB memory in use. Of the allocated memory 22.02 GiB is allocated by PyTorch, and 4.91 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: