dbmdz/convbert-base-german-europeana-cased

In this repository the MDZ Digital Library team (dbmdz) at the Bavarian State.Library open sources a German Europeana ConvBERT model . The final training corpus has a size of 51GB and consists of 8,035,986,369 tokens . For results on Historic NER, please refer to this repository . For questions about our Europeana BERT, ELECTRA and convBERT models just open a new discussion about the model here . The Hugging Face model hub is available on the Huggingface model hub. For more information about the data and pretraining steps can be found in this repository. It is possible to download both cased and uncased models from,