<?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>GPT on zsai blog</title><link>https://idev.sh/tags/gpt/</link><description>Recent content in GPT on zsai blog</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Sat, 27 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://idev.sh/tags/gpt/index.xml" rel="self" type="application/rss+xml"/><item><title>Transformer 系列(八):从 Transformer 到 GPT 与 BERT</title><link>https://idev.sh/posts/transformer-08-gpt-bert/</link><pubDate>Sat, 27 Jun 2026 00:00:00 +0000</pubDate><guid>https://idev.sh/posts/transformer-08-gpt-bert/</guid><description>同一套积木,三种拼法。Encoder-only、Decoder-only、Encoder-Decoder 各自擅长什么?为什么今天的大模型几乎都是 Decoder-only?</description></item></channel></rss>