runtime error

Exit code: 1. Reason: ts, so we will NOT tie them. You should update the config with `tie_word_embeddings=False` to silence this warning PegasusForConditionalGeneration LOAD REPORT from: google/pegasus-billsum Key | Status | -------------------------------------+---------+- model.decoder.embed_positions.weight | MISSING | model.encoder.embed_positions.weight | MISSING | Notes: - MISSING :those params were newly initialized because missing from the checkpoint. Consider training on your downstream task. generation_config.json: 0%| | 0.00/280 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 280/280 [00:00<00:00, 956kB/s] Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. tokenizer_config.json: 0%| | 0.00/88.0 [00:00<?, ?B/s] tokenizer_config.json: 100%|██████████| 88.0/88.0 [00:00<00:00, 304kB/s] spiece.model: 0%| | 0.00/1.91M [00:00<?, ?B/s] spiece.model: 100%|██████████| 1.91M/1.91M [00:00<00:00, 41.5MB/s] special_tokens_map.json: 0%| | 0.00/65.0 [00:00<?, ?B/s] special_tokens_map.json: 100%|██████████| 65.0/65.0 [00:00<00:00, 203kB/s] Traceback (most recent call last): File "/app/app.py", line 12, in <module> text_summary = pipeline(task="any-to-any", model="google/pegasus-billsum") File "/usr/local/lib/python3.13/site-packages/transformers/pipelines/__init__.py", line 1006, in pipeline raise e File "/usr/local/lib/python3.13/site-packages/transformers/pipelines/__init__.py", line 999, in pipeline raise TypeError( ...<3 lines>... ) TypeError: Processor was loaded, but it is not an instance of `ProcessorMixin`. Got type `<class 'transformers.models.pegasus.tokenization_pegasus.PegasusTokenizer'>` instead. Please check that you specified correct pipeline task for the model and model has processor implemented and saved.

Container logs: