deepampatel/roberta-mlm-mr

This is a small language model for Marathi language with 1M data samples taken from OSCAR page . Data set is of 2.7 GB due to resource constraint to train model . ByteLevelBPETokenizer is used to tokenize the sentences at character level and vocabulary size is set to 52k . This is for anyone who wants to make use of marathi language models for various tasks like language generation, translation and many more use cases . If you are interested in collaboration and have computational resources to train on you are most welcome to do so, please contact Deepam Deepam at resear-marathi-MLM.com/roopa/arathi-model,