dbmdz/german-gpt2

The German GPT-2 model was trained on various texts for German . The model is meant to be an entry point for fine-tuning on other texts . We use the same corpora as used for training the DBMDZ BERT model, that can be found in this repository . We do not plan extensive PR or staged releases for this model . It was initially released under an anonymous alias so we now "de-anonymize" it . It is not as good or "dangerous" as the English Gpt-3 model, and it is not a good or dangerous option . It's possible to use the awesome Tokenizers library to create byte-level BPE,