<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>实战指南 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%AE%9E%E6%88%98%E6%8C%87%E5%8D%97/</link><description>Recent content in 实战指南 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Thu, 02 Jul 2026 10:49:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%AE%9E%E6%88%98%E6%8C%87%E5%8D%97/index.xml" rel="self" type="application/rss+xml"/><item><title>从零搭建RAG系统2026：端到端实战指南</title><link>https://guijiagi.com/posts/rag-from-scratch-2026/</link><pubDate>Thu, 02 Jul 2026 10:49:00 +0800</pubDate><guid>https://guijiagi.com/posts/rag-from-scratch-2026/</guid><description>从零开始搭建生产级RAG系统的完整实战指南，覆盖架构、实现与优化</description></item><item><title>QLoRA量化微调实战：显存减半效果不减</title><link>https://guijiagi.com/posts/qlora-quantized-finetuning-guide/</link><pubDate>Tue, 30 Jun 2026 09:40:00 +0800</pubDate><guid>https://guijiagi.com/posts/qlora-quantized-finetuning-guide/</guid><description>QLoRA让7B模型微调只需8GB显存，70B模型只需24GB，本文详解QLoRA原理与实战配置</description></item></channel></rss>