@inproceedings{oneill-dutta-2023-self, title = "Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models", author = "O{'}Neill, James and Dutta, Sourav", editor = "Rogers, Anna and Boyd-Graber, Jordan and Okazaki, Naoaki", booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)", month = jul, year = "2023", address = "Toronto, Canada", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2023.acl-short.114/", doi = "10.18653/v1/2023.acl-short.114", pages = "1329--1339" }