Activation-Guided Low-Rank Parameter Adaptation for Efficient Model Fine-Tuning

Fine-tuning large language models is computationally expensive, and while existing parameter-efficient methods like Low-Rank Adaptation (LoRA) reduce computational costs, they are limited by suboptimal initialization strategies. We introduce Activation-Guided LoRA (AG-LoRA), a novel approach that in...

全面介紹

書目詳細資料

Principais autores:	Qingchen Wang, Shengyu Shen
格式:	Artigo
語言:	Inglês
出版:	IEEE 2025-01-01
叢編:	IEEE Access
主題:	Deep learning low-rank adaptation parameter-efficient fine-tuning
在線閱讀:	https://ieeexplore.ieee.org/document/10852296/
標簽:	添加標簽 沒有標簽, 成為第一個標記此記錄!