The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models

The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models Eldar Kurtic author Daniel Campos author Tuan Nguyen author Elias Frantar author Mark Kurtz author Benjamin Fineran author Michael Goin author Dan Alistarh author 2022-12 text Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing Yoav Goldberg editor Zornitsa Kozareva editor Yue Zhang editor Association for Computational Linguistics Abu Dhabi, United Arab Emirates conference publication kurtic-etal-2022-optimal 10.18653/v1/2022.emnlp-main.279 https://aclanthology.org/2022.emnlp-main.279/ 2022-12 4163 4181