runtime error

Exit code: 1. Reason: A Batches: 99%|█████████▊| 617/625 [23:07<00:05, 1.51it/s] Batches: 99%|█████████▉| 620/625 [23:08<00:02, 1.69it/s] Batches: 100%|█████████▉| 622/625 [23:09<00:01, 1.74it/s] Batches: 100%|██████████| 625/625 [23:10<00:00, 2.04it/s] Batches: 100%|██████████| 625/625 [23:10<00:00, 2.23s/it] Embeddings ready. Loading QA model (Flan-T5-small)... config.json: 0.00B [00:00, ?B/s] config.json: 1.40kB [00:00, 1.25MB/s] Traceback (most recent call last): File "/app/app.py", line 44, in <module> llm = pipeline( "text2text-generation", model="google/flan-t5-small", ) File "/usr/local/lib/python3.13/site-packages/transformers/pipelines/__init__.py", line 747, in pipeline normalized_task, targeted_task, task_options = check_task(task) ~~~~~~~~~~^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/pipelines/__init__.py", line 355, in check_task return PIPELINE_REGISTRY.check_task(task) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/pipelines/base.py", line 1338, in check_task raise KeyError(f"Unknown task {task}, available tasks are {self.get_supported_tasks()}") KeyError: "Unknown task text2text-generation, available tasks are ['any-to-any', 'audio-classification', 'automatic-speech-recognition', 'depth-estimation', 'document-question-answering', 'feature-extraction', 'fill-mask', 'image-classification', 'image-feature-extraction', 'image-segmentation', 'image-text-to-text', 'keypoint-matching', 'mask-generation', 'ner', 'object-detection', 'sentiment-analysis', 'table-question-answering', 'text-classification', 'text-generation', 'text-to-audio', 'text-to-speech', 'token-classification', 'video-classification', 'zero-shot-audio-classification', 'zero-shot-classification', 'zero-shot-image-classification', 'zero-shot-object-detection']"

Container logs: