<?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>大模型微调 on 厨师海森堡的厨房</title>
    <link>https://kevinchen1994.github.io/tags/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BE%AE%E8%B0%83/</link>
    <description>Recent content in 大模型微调 on 厨师海森堡的厨房</description>
    <image>
      <title>厨师海森堡的厨房</title>
      <url>https://kevinchen1994.github.io/images/profile.jpg</url>
      <link>https://kevinchen1994.github.io/images/profile.jpg</link>
    </image>
    <generator>Hugo -- 0.161.1</generator>
    <language>zh-cn</language>
    <lastBuildDate>Fri, 25 Aug 2023 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://kevinchen1994.github.io/tags/%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%BE%AE%E8%B0%83/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>PEFT</title>
      <link>https://kevinchen1994.github.io/posts/peft/</link>
      <pubDate>Fri, 25 Aug 2023 00:00:00 +0000</pubDate>
      <guid>https://kevinchen1994.github.io/posts/peft/</guid>
      <description>对于大模型微调起来不仅需要很多计算资源（GPU），还需要大量的训练时间，PEFT通过高效微调模型，使得我们可以使用单卡去训练比较大的LLM。</description>
    </item>
  </channel>
</rss>
