<?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>LoRA on Pranav Buradkar</title>
    <link>https://pranavburadkar.github.io/tags/lora/</link>
    <description>Recent content in LoRA on Pranav Buradkar</description>
    <generator>Hugo -- 0.164.0</generator>
    <language>en-us</language>
    <lastBuildDate>Sun, 12 Apr 2026 10:00:00 +0530</lastBuildDate>
    <atom:link href="https://pranavburadkar.github.io/tags/lora/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>How to Fine-Tune Llama 3 on Your Own Data: A Practical Guide</title>
      <link>https://pranavburadkar.github.io/posts/fine-tune-llama-3-lora/</link>
      <pubDate>Sun, 12 Apr 2026 10:00:00 +0530</pubDate>
      <guid>https://pranavburadkar.github.io/posts/fine-tune-llama-3-lora/</guid>
      <description>Step-by-step practical guide to fine-tuning Meta&amp;#39;s Llama 3 using PyTorch, Hugging Face Transformers, and PEFT/LoRA on a custom dataset.</description>
    </item>
    <item>
      <title>A Simple Guide to LoRA (Low-Rank Adaptation)</title>
      <link>https://pranavburadkar.github.io/posts/understanding-lora-fine-tuning/</link>
      <pubDate>Fri, 20 Mar 2026 10:00:00 +0530</pubDate>
      <guid>https://pranavburadkar.github.io/posts/understanding-lora-fine-tuning/</guid>
      <description>Learn how Low-Rank Adaptation (LoRA) makes fine-tuning massive LLMs and generative models incredibly efficient.</description>
    </item>
  </channel>
</rss>
