uaritm/ukrt5-base

1---2language:3- uk4- en5- multilingual6license: mit7tags:8- ukrainian9- english10---11 12This is a variant of the [google/mt5-base](https://huggingface.co/google/mt5-base) model, in which Ukrainian and 9% English words remain.13This model has 252M parameters - 43% of the original size.14Special thanks for the practical example and inspiration: [cointegrated ](https://huggingface.co/cointegrated)15 16## Citing & Authors17```18@misc{Uaritm,19      title={SetFit: Classification of medical texts}, 20      author={Vitaliy Ostashko},21      year={2022},22      url={https://esemi.org}23}24```25