abhishekkrthakur/tez

Text classification examples - Tokenizer is defined twice

obesp opened this issue · 1 comments

obesp commented

The tokenizer is defined both in the model and the dataset in the BERT text classification examples.

multi_class.py, line 50:
self.tokenizer = transformers.BertTokenizer.from_pretrained( "bert-base-uncased", do_lower_case=True )

Indeed it is. its not needed in model. seems like a copy-paste error. ;) i will fix it.