Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging

Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging Deyuan Liu author Zhanyue Qin author Hairu Wang author Zhao Yang author Zecheng Wang author Fangying Rong author Qingbin Liu author Yanchao Hao author Bo Li author Xi Chen author Cunhang Fan author Zhao Lv author Dianhui Chu author Zhiying Tu author Dianbo Sui author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication liu-etal-2024-pruning 10.18653/v1/2024.emnlp-main.987 https://aclanthology.org/2024.emnlp-main.987/ 2024-11 17817 17829