Loading donut transformers model getting error

self.model = self.model.to(self.device) File “/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py”, line 1145, in to return self._apply(convert) File “/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py”, line 797, in _apply module._apply(fn) File “/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py”, line 797, in _apply module._apply(fn) File “/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py”, line 797, in _apply module._apply(fn) [Previous line repeated 1 more time] File “/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py”, line 820, in _apply param_applied = fn(param) File “/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py”, line 1143, in convert return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking) RuntimeError: CUDA error: device-side assert triggered Compile with TORCH_USE_CUDA_DSA to enable device-side assertions. code:- class Donut: def __init__(self): try: self.processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa") self.model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa") self.device = "cuda" if torch.cuda.is_available() else "cpu" if torch.cuda.is_available(): try: self.device = torch.device("cuda") self.model = self.model.to(self.device) torch.cuda.empty_cache() except RuntimeError as e: console_logger.warning(f"{str(e)}") except Exception as e: console_logger.error(f"Failed to initialize Donut: {str(e)}") raise Versions:- torch==2.0.1+cu118 torchaudio==2.0.2+cu118 torchvision==0.15.2+cu118 transformers==4.24.0 Nvidia Driver :- Driver Version: 550.144.03 CUDA Version: 12.4 Docker image :- nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu22.04