monsoon-nlp/muril-adapted-local

Google open sourced a BERT model pre-trained on 17 Indian languages . The model was trained using a self-supervised masked language modeling task . It was trained for 1000K steps, with a batch size of 4096, and a max sequence length of 512 . I ported the TFHub .pb model to .h5 and then pytorch_model.bin for compatibility with Transformers. The model has been hosted on HuggingFace: https://huggingface.co/simran-kh/muril-with-mlm-cased-temp .License: Apache 2.0/ / /python/python/Python/Python: Python/Python-Python/,