bayartsogt/albert-mongolian

We provide pretrained ALBERT model and trained SentencePiece model for Mongolia text . Training data is the Mongolian wikipedia corpus from Wikipedia Downloads and Mongolian News corpus . AlberT-Mongolian-language-based model is pretrained on Mongolian Text Classification's paper . AlBERT is a pre-trained model for Japanese Text Classification and Sentence-Piece Model for Mongolian text . The model is based on the data from Wikipedia's Mongolian Wikipedia, Mongolian news, and its training data from Mongolian Wikipedia downloads . The training data is available in the official repo of the official repository. The model's training code is available on GitHub,