The SAS Deep Learning Python (DLPy) package provides the high-level Python APIs to deep learning methods in SAS Visual Data Mining and Machine Learning. It allows users to build deep learning models using friendly Keras-like APIs.
When we need to use different type of BERT (cl-tohoku/bert-base-japanese, for instance), since they have different tokenizer from the one that the original BERT uses, users cannot call those models via DLPy's transformer. Auto classes can take care around this. (I think this also applies to roberta, distilbert as well, but didn't make it myself.)
When we need to use different type of BERT (cl-tohoku/bert-base-japanese, for instance), since they have different tokenizer from the one that the original BERT uses, users cannot call those models via DLPy's transformer. Auto classes can take care around this. (I think this also applies to roberta, distilbert as well, but didn't make it myself.)