bert-base-german-cased
Bert-base-german-cased is machine learning model.
About bert-base-german-cased
Language model: bert-base-casedLanguage: German . Training data: Wiki, OpenLegalData, News (~ 12GB)Eval data: Conll03 (NER), GermEval14 (NER) and Germeval18 (Classification)Infrastructure: 1x TPU v2 with standard settings . Update April 3rd, 2020: we updated the vocabulary file on deepset's s3 to conform with the default tokenization of punctuation tokens . If you want to use the old vocab we have also uploaded a "deepset/bert-Base-german-Cased-oldvocab" model . We trained using Google's Tensorflow,