A Computational Study of Matrix Decomposition Methods for Compression of Pre-trained Transformers

Sergey Pletenev, Viktoria Chekalina, Daniil Moskovskiy, Mikhail Seleznev, Sergey Zagoruyko, Alexander Panchenko. A Computational Study of Matrix Decomposition Methods for Compression of Pre-trained Transformers. In Chu-Ren Huang, Yasunari Harada, Jong-Bok Kim, Si Chen, Yu-Yin Hsu, Emmanuele Chersoni, Pranav A, Winnie Huiheng Zeng, Bo Peng, Yuxi Li, Junlin Li, editors, Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation, PACLIC 2023, The Hong Kong Polytechnic University, Hong Kong, SAR, China, 2-4 December 2023. pages 723-742, Association for Computational Linguistics, 2023. [doi]

Abstract

Abstract is missing.