asafaya/bert-medium-arabic

Arabic BERT Medium Model for Arabic language model for Arabic . It was trained using Google BERT's GitHub repository on a single TPU v3-8 provided for free from TFRC . The model was pretrained on 8.2 Billion words: Arabic version of OSCAR - filtered from Common Crawl . The final version of corpus contains some non-Arabic words inlines, which we did not remove from sentences . There is no cased and uncased version of the model . You can use this model by installing torch or tensorflow and Huggingface library transformers . For further details on the models performance or any other queries, please refer to Arabic-BERT,