# TaMillion

This is a first attempt at a Tamil language model trained with
Google Research's [ELECTRA](https://github.com/google-research/electra).

Tokenization and pre-training CoLab: https://colab.research.google.com/drive/1GngBFn_Ge5Hd2XI2febBhZyU7GDiqw5w

V2 (current): 190,000 steps

V1: 100,000 steps;

## Usage

Sudalai Rajkumar's Tamil-NLP page contains classification and regression tasks:
https://www.kaggle.com/sudalairajkumar/tamil-nlp

Notebook: https://colab.research.google.com/drive/1_rW9HZb6G87-5DraxHvhPOzGmSMUc67_?usp=sharin

The model outperformed mBERT on news classification:
(Random: 16.7%, mBERT: 53.0%, TaMillion: 68.2%)

The model slightly outperformed mBERT on movie reviews:
(RMSE - mBERT: 0.657, TaMillion: 0.626)

Equivalent accuracy on the Tirukkural topic task.

## Corpus

Trained on a web crawl from https://oscar-corpus.com/ (deduped version, 5.1GB) and 1 July 2020 dump of ta.wikipedia.org (476MB)

## Vocabulary

Included as vocab.txt in the upload - vocab_size is 40161