<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>数据STUDIO on 文字轨迹</title><link>https://ixxmu.github.io/tags/%E6%95%B0%E6%8D%AEstudio/</link><description>Recent content in 数据STUDIO on 文字轨迹</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Fri, 18 Apr 2025 02:34:42 +0000</lastBuildDate><atom:link href="https://ixxmu.github.io/tags/%E6%95%B0%E6%8D%AEstudio/index.xml" rel="self" type="application/rss+xml"/><item><title>Python 实现 GRPO 简版</title><link>https://ixxmu.github.io/posts/2025-04/python_%E5%AE%9E%E7%8E%B0_grpo_%E7%AE%80%E7%89%88/</link><pubDate>Fri, 18 Apr 2025 02:34:42 +0000</pubDate><guid>https://ixxmu.github.io/posts/2025-04/python_%E5%AE%9E%E7%8E%B0_grpo_%E7%AE%80%E7%89%88/</guid><description>Python 实现 GRPO 简版 by 数据STUDIO 今天我们将深入探讨GRPO的实现。先简要介绍这一概念，讨论方法，然后开始具体实现。</description></item></channel></rss>