The aim is to compress the mT5-large model to leave only the Ukrainian language and some basic English.
Reproduced the similar result (but with another language) from this medium article.
Results:
- 1.2B params -> 779M params (37%)
- 250K tokens -> 8900 tokens
- 4.6GB size model -> 2.9GB size model
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support