<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>训练稳定性 on 王二的自留地</title><link>http://wanger.dev/tags/%E8%AE%AD%E7%BB%83%E7%A8%B3%E5%AE%9A%E6%80%A7/</link><description>Recent content in 训练稳定性 on 王二的自留地</description><generator>Hugo -- gohugo.io</generator><language>zh-CN</language><copyright>&amp;copy; 2026 Wanger &amp;middot; [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)</copyright><lastBuildDate>Mon, 27 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="http://wanger.dev/tags/%E8%AE%AD%E7%BB%83%E7%A8%B3%E5%AE%9A%E6%80%A7/index.xml" rel="self" type="application/rss+xml"/><item><title>18 归一化的选择：LayerNorm → RMSNorm，Pre-LN vs Post-LN</title><link>http://wanger.dev/llm/llm_18/</link><pubDate>Mon, 27 Jul 2026 00:00:00 +0000</pubDate><guid>http://wanger.dev/llm/llm_18/</guid><description/><media:content xmlns:media="http://search.yahoo.com/mrss/" url="http://wanger.dev/llm/llm_18/feature-prenorm-narrowband.png"/></item></channel></rss>