runtime error

Exit code: 1. Reason: ing bytes: ████████ | 279MB, 23.4MB/s model.safetensors: downloading bytes: ██████████| 328MB, 30.0MB/s model.safetensors: downloading bytes: ██████████| 328MB, 30.0MB/s model.safetensors: reconstructing file: 100%|██████████| 346MB / 346MB, 32.5MB/s Loading weights: 0%| | 0/198 [00:00<?, ?it/s] Loading weights: 100%|██████████| 198/198 [00:00<00:00, 4794.38it/s] [transformers] ViTModel LOAD REPORT from: google/vit-base-patch16-224 Key | Status | --------------------+------------+- classifier.bias | UNEXPECTED | classifier.weight | UNEXPECTED | pooler.dense.weight | MISSING | pooler.dense.bias | MISSING | Notes: - UNEXPECTED: can be ignored when loading from different task/architecture; not ok if you expect identical arch. - MISSING: those params were newly initialized because missing from the checkpoint. Consider training on your downstream task. config.json: 0%| | 0.00/665 [00:00<?, ?B/s] config.json: 100%|██████████| 665/665 [00:00<00:00, 2.12MB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 54, in <module> model = VisionEncoderDecoderModel.from_encoder_decoder_pretrained(encoder_name_or_path,decoder_name_or_path) File "/usr/local/lib/python3.10/site-packages/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py", line 272, in from_encoder_decoder_pretrained if decoder_config.is_decoder is False or decoder_config.add_cross_attention is False: File "/usr/local/lib/python3.10/site-packages/transformers/configuration_utils.py", line 652, in __getattribute__ return super().__getattribute__(key) File "/usr/local/lib/python3.10/site-packages/transformers/integrations/heterogeneity/configuration_utils.py", line 312, in __getattribute__ return super().__getattribute__(key) AttributeError: 'GPT2Config' object has no attribute 'is_decoder'

Container logs: