Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models Kai Yao author Penglei Gao author Lichun Li author Yuan Zhao author Xiaofeng Wang author Wei Wang author Jianke Zhu author 2024-11 text Findings of the Association for Computational Linguistics: EMNLP 2024 Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication yao-etal-2024-layer 10.18653/v1/2024.findings-emnlp.109 https://aclanthology.org/2024.findings-emnlp.109/ 2024-11 1977 1992