This repository contains code for the paper A Comprehensive Analysis of Adapter Efficiency.
IndicBert contains code for Adapter tuning, Fine-tuning and multitask training for IndicBert model.
XLMR contains code for Adapter tuning, Fine-tuning and multitask training for XLMR-Base and XLMR-Large model.
Nandini Mundra ([email protected])
Sumanth Doddapaneni
Raj Dabre
Anoop Kunchukuttan
Ratish Puduppully
Mitesh M. Khapra
code will be release under an MIT license
We would like to thank the Ministry of Electronics and Information Technology https://www.meity.gov.in/ of the Government of India for their generous grant through the Digital India Bhashini project https://www.bhashini.gov.in/ . We also thank the Centre for Development of Advanced Computing https://www.cdac.in/index.aspx?id=pune for providing compute time on the Param Siddhi Supercomputer. We also thank Nilekani Philanthropies for their generous grant towards building datasets, models, tools and resources for Indic languages. We also thank Microsoft for their grant to support research on Indic languages.
This repository contains code for the paper A Comprehensive Analysis of Adapter Efficiency.
IndicBert contains code for Adapter tuning, Fine-tuning and multitask training for IndicBert model.
XLMR contains code for Adapter tuning, Fine-tuning and multitask training for XLMR-Base and XLMR-Large model.
Nandini Mundra ([email protected])
Sumanth Doddapaneni
Raj Dabre
Anoop Kunchukuttan
Ratish Puduppully
Mitesh M. Khapra
code will be release under an MIT license
We would like to thank the Ministry of Electronics and Information Technology https://www.meity.gov.in/ of the Government of India for their generous grant through the Digital India Bhashini project https://www.bhashini.gov.in/ . We also thank the Centre for Development of Advanced Computing https://www.cdac.in/index.aspx?id=pune for providing compute time on the Param Siddhi Supercomputer. We also thank Nilekani Philanthropies for their generous grant towards building datasets, models, tools and resources for Indic languages. We also thank Microsoft for their grant to support research on Indic languages.
