Tokenizer Files
Hello,
Can you please upload the special_tokens_map.json, tokenizer_config.json and vocab.json files? I tried to download and use this model, but I got a "keyerror" message related to missing tokenizer configurations.
Exact Error Message:
´´´
KeyError Traceback (most recent call last)
in <cell line: 1>()
----> 1 processor = TrOCRProcessor.from_pretrained('crystalchen/trocr-tc-small')
3 frames
/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py in getitem(self, key)
769 model_name = self._model_mapping[mtype]
770 return self._load_attr_from_module(mtype, model_name)
--> 771 raise KeyError(key)
772
773 def _load_attr_from_module(self, model_type, attr):
KeyError: <class 'transformers.models.vision_encoder_decoder.configuration_vision_encoder_decoder.VisionEncoderDecoderConfig'>
´´´
Explanation Provided by Google Gemini:
"The error message KeyError: <class 'transformers.models.vision_encoder_decoder.configuration_vision_encoder_decoder.VisionEncoderDecoderConfig'> indicates that the TOKENIZER_MAPPING dictionary in transformers.models.auto.tokenization_auto does not have an entry for the VisionEncoderDecoderConfig class. This usually happens when the required tokenizer for the specified model architecture (VisionEncoderDecoder) is not registered or available within the Transformers library."
Thanks in advance.