Published in arxiv preprint, 2024
We scale sparse fine-tuning methods for 7b and 13b Llama 2, such that the memory requirements scale linearly with the number of paramerters updated by the fine-tuning.
Published in In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2023
We introduce Adapters, an open-source library that unifies parameter-efficient and modular transfer learning in large language models.
Published in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2022
We present UKP-SQUARE, an extensible online QA platform for researchers which allows users to query and analyze a large collection of modern Skills via a user-friendly web interface and integrated behavioural tests.