About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Clifton Poth
- sl:arxiv_num : 2311.11077
- sl:arxiv_published : 2023-11-18T13:53:26Z
- sl:arxiv_summary : We introduce Adapters, an open-source library that unifies
parameter-efficient and modular transfer learning in large language models. By
integrating 10 diverse adapter methods into a unified interface, Adapters
offers ease of use and flexible configuration. Our library allows researchers
and practitioners to leverage adapter modularity through composition blocks,
enabling the design of complex adapter setups. We demonstrate the library's
efficacy by evaluating its performance against full fine-tuning on various NLP
tasks. Adapters provides a powerful tool for addressing the challenges of
conventional fine-tuning paradigms and promoting more efficient and modular
transfer learning. The library is available via https://adapterhub.ml/adapters.@en
- sl:arxiv_title : Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning@en
- sl:arxiv_updated : 2023-11-18T13:53:26Z
- sl:bookmarkOf : https://arxiv.org/abs/2311.11077
- sl:creationDate : 2023-11-25
- sl:creationTime : 2023-11-25T09:14:07Z
Documents with similar tags (experimental)
Preferences...