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 specifying a huggingface model, only the models starting with bert-, roberta- and distil- are supported. However, it would enable users to develop models for other languages as well if that restriction was removed. For example, the Finnish model is similar size to bert-uncased, but its name starts with "TurkuNLP/bert" so it cannot be used yet.
When specifying a huggingface model, only the models starting with bert-, roberta- and distil- are supported. However, it would enable users to develop models for other languages as well if that restriction was removed. For example, the Finnish model is similar size to bert-uncased, but its name starts with "TurkuNLP/bert" so it cannot be used yet.![berterror](https://user-images.githubusercontent.com/81144914/111951230-0bcf9300-8aec-11eb-8982-7ead98297a90.PNG)