<?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>训练流程 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E8%AE%AD%E7%BB%83%E6%B5%81%E7%A8%8B/</link><description>Recent content in 训练流程 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>Sun, 28 Jun 2026 11:10:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E8%AE%AD%E7%BB%83%E6%B5%81%E7%A8%8B/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型训练流程：预训练/SFT/RLHF/DPO 全链路</title><link>https://guijiagi.com/posts/llm-training-pipeline-pretrain-sft-rlhf-dpo/</link><pubDate>Sun, 28 Jun 2026 11:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/llm-training-pipeline-pretrain-sft-rlhf-dpo/</guid><description>系统解析大模型训练的四个阶段：预训练、监督微调、RLHF、DPO的原理、流程与2026年最佳实践</description></item></channel></rss>