LoRA: Low-Rank Adaptation (2021)
研究论文
系统
Fine-tuning for the GPU-poor — tiny adapters instead of full weights.
您正在查看一条研究论文记录:一篇里程碑式的论文,以及它为该领域带来了什么。
Microsoft researchers showed models adapt through low-rank update matrices a thousandth the size of the weights — making fine-tuning accessible to anyone with one GPU and creating the adapter ecosystems around Llama and Stable Diffusion.
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
基础来源
来源
记录审阅截至 2026-01-15 — 查看 方法论.