bangla-electra / README.md
system's picture
system HF staff
Update README.md
a6591f9
|
raw
history blame
899 Bytes

Bangla-Electra

This is a second attempt at a Bangla/Bengali language model trained with Google Research's ELECTRA.

Tokenization and pre-training CoLab: https://colab.research.google.com/drive/1gpwHvXAnNQaqcu-YNx1kafEVxz07g2jL

V1 - 120,000 steps V2 - 190,000 steps

Benchmarks

Classification with SimpleTransformers: https://colab.research.google.com/drive/1vltPI81atzRvlALv4eCvEB0KdFoEaCOb

On Soham Chatterjee's news classification task: (Random: 16.7%, mBERT: 72.3%, Bangla-Electra: 82.3%)

Similar to mBERT on some tasks and configurations described in https://arxiv.org/abs/2004.07807

Corpus

Trained on a web crawl from https://oscar-corpus.com/ (deduped version, 5.8GB) and 1 July 2020 dump of bn.wikipedia.org (414MB)

Vocabulary

Included as vocab.txt in the upload - vocab_size is 29898