<?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>Epoch AI on FisherAI</title>
    <link>https://fisherdaddy.com/tags/epoch-ai/</link>
    <description>Recent content in Epoch AI on FisherAI</description>
    <image>
      <title>FisherAI</title>
      <url>https://fisherdaddy.com/images/papermod-cover.png</url>
      <link>https://fisherdaddy.com/images/papermod-cover.png</link>
    </image>
    <generator>Hugo -- 0.125.7</generator>
    <language>en</language>
    <lastBuildDate>Sat, 01 Feb 2025 10:22:32 +0800</lastBuildDate>
    <atom:link href="https://fisherdaddy.com/tags/epoch-ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>DeepSeek-R1 的训练过程是怎样的？• Epoch AI</title>
      <link>https://fisherdaddy.com/posts/what-went-into-training-deepseek-r1-by-epochai/</link>
      <pubDate>Sat, 01 Feb 2025 10:22:32 +0800</pubDate>
      <guid>https://fisherdaddy.com/posts/what-went-into-training-deepseek-r1-by-epochai/</guid>
      <description>深入解析DeepSeek-R1的训练过程，包括其架构、预训练、强化学习阶段，并探讨了其成本、性能和定价策略。揭秘DeepSeek-R1如何以更低的成本达到与OpenAI o1相当的性能。</description>
    </item>
  </channel>
</rss>
