tugstugi/bert-base-mongolian-uncased

This repository contains pre-trained Mongolian BERT models trained by tugstugi, enod and sharavsambuu . The repository is based on the following open source projects: google-research/bert, huggingface/pytorch-pretrained-BERT and yoheikikuta/bert-japanese. The Mongolian-BASE-Mongolian-UNCASED repository is open source and is hosted by Tuguldur, Erdene-Ochir and Gunchinish. The repository contains training data from the Mongolian Wikipedia and the 700 million word Mongolian news data set . For more information, visit http://www,