voidful/albert_chinese_large

This is a albert_chinese_large model from Google's Githubconverted by huggingface's script . Since sentencepiece is not used in albert chinese large modelyou have to call BertTokenizer instead of AlbertTokenizer . We can eval it using an example on MaskedLM . The result is 0.9422469735145569 . The model is a 'voidful' model with an 'AlbertForMaskedLM' model . It can be used to create a new version of the previous version of Albert_Chinese_Large . The code is based on a model from the previous Albert model. It is now being used,