<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LoRA - 标签 - 南冥鹏影</title><link>https://fupcode.com/blog/tags/lora/</link><description>南冥鹏影</description><generator>Hugo 0.168.0 &amp; FixIt v1.0.0-beta.4</generator><language>zh-CN</language><lastBuildDate>Thu, 20 Nov 2025 19:05:47 +0800</lastBuildDate><atom:link href="https://fupcode.com/blog/tags/lora/index.xml" rel="self" type="application/rss+xml"/><item><title>LoRA 原理与实战</title><link>https://fupcode.com/blog/posts/deep-learning/lora/</link><pubDate>Thu, 20 Nov 2025 19:05:47 +0800</pubDate><guid>https://fupcode.com/blog/posts/deep-learning/lora/</guid><category domain="https://fupcode.com/blog/categories/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/">深度学习</category><description>&lt;p&gt;在深度学习微调大模型时，&lt;strong&gt;LoRA（Low-Rank Adaptation）&lt;/strong&gt; 提供了一种高效、轻量的微调方法。本文讲述了LoRA的原理，同时结合一个小型 MNIST 实验做了验证。&lt;/p&gt;</description></item></channel></rss>