<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>spider on David An</title>
    <link>https://davidan.dev/tags/spider/</link>
    <description>Recent content in spider on David An</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 12 Jan 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://davidan.dev/tags/spider/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Fine Tuning Llama 3.2B with Unsloth</title>
      <link>https://davidan.dev/posts/ftsql/</link>
      <pubDate>Mon, 12 Jan 2026 00:00:00 +0000</pubDate>
      
      <guid>https://davidan.dev/posts/ftsql/</guid>
      <description>In this article, we will be fine tuning the Llama 3.2B model with Unsloth on the Spider 1.0 SQL dataset. The goal of the article is to improve the SQL capabilities of a general Llama 3.2B model.
Prerequisites Before we get started, we assume that the reader has access to a GPU which they are able to use for training. Additionally, we assume that the reader has a Python setup.</description>
    </item>
    
  </channel>
</rss>
