BriefGPT.xyz
Aug, 2023
大语言模型的贝叶斯低秩适应
Bayesian low-rank adaptation for large language models
HTML
PDF
Adam X. Yang, Maxime Robeyns, Xi Wang, Laurence Aitchison
TL;DR
使用Laplace-LoRA方法，对参数高效微调的大型语言模型进行贝叶斯方法，提高模型的校准性。
Abstract
parameter-efficient fine-tuning
(PEFT) has emerged as a new paradigm for cost-efficient fine-tuning of
large language models
(LLMs), with
low-ran
→