thevasudevgupta/transformers-adapters

This repositary hosts my experiments for the project, I did with OffNote Labs.

27
/ 100
Experimental

This project helps machine learning engineers and NLP researchers efficiently adapt large language models for specific translation tasks. It allows you to take a base multilingual model and add smaller, specialized adapter modules. This results in a translation model that takes text in languages like Hindi or Gujarati and outputs English text, but with significantly reduced model size and faster training compared to full model fine-tuning.

No commits in the last 6 months.

Use this if you need to perform neural machine translation for Indian languages into English and want to optimize for computational efficiency and speed.

Not ideal if you need a pre-packaged, ready-to-use translation API or a solution for a wide variety of less common language pairs.

neural-machine-translation natural-language-processing multilingual-translation language-model-adaptation computational-linguistics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

10

Forks

3

Language

Python

License

Last pushed

Apr 12, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/thevasudevgupta/transformers-adapters"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.