Poth, Clifton ; Sterz, Hannah ; Paul, Indraneil ; Purkayastha, Sukannya ; Englander, Leon ; Imhof, Timo ; Vulić, Ivan ; Ruder, Sebastian ; Gurevych, Iryna ; Pfeiffer, Jonas (2023)
Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning.
2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Singapore (06.-10.12.2023)
doi: 10.18653/v1/2023.emnlp-demo.13
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
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.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2023 |
| Autor(en): | Poth, Clifton ; Sterz, Hannah ; Paul, Indraneil ; Purkayastha, Sukannya ; Englander, Leon ; Imhof, Timo ; Vulić, Ivan ; Ruder, Sebastian ; Gurevych, Iryna ; Pfeiffer, Jonas |
| Art des Eintrags: | Bibliographie |
| Titel: | Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning |
| Sprache: | Englisch |
| Publikationsjahr: | Dezember 2023 |
| Ort: | Singapore |
| Verlag: | Association for Computational Linguistics |
| Buchtitel: | Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations |
| Veranstaltungstitel: | 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations |
| Veranstaltungsort: | Singapore |
| Veranstaltungsdatum: | 06.-10.12.2023 |
| DOI: | 10.18653/v1/2023.emnlp-demo.13 |
| URL / URN: | https://aclanthology.org/2023.emnlp-demo.13 |
| Kurzbeschreibung (Abstract): | 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. |
| Freie Schlagworte: | UKP_p_HUAWEI, UKP_p_KRITIS |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 18 Jan 2024 14:13 |
| Letzte Änderung: | 11 Apr 2024 12:34 |
| PPN: | 517105837 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum