<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Large Language Models on /home/vigi99</title><link>https://viig99.github.io/tags/large-language-models/</link><description>Recent content in Large Language Models on /home/vigi99</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 17 Jun 2024 10:03:05 -0400</lastBuildDate><atom:link href="https://viig99.github.io/tags/large-language-models/index.xml" rel="self" type="application/rss+xml"/><item><title>Supervised Fine-Tuning in Large Language Models</title><link>https://viig99.github.io/docs/posts/supervised_finetuning/</link><pubDate>Mon, 22 May 2023 00:00:00 +0000</pubDate><guid>https://viig99.github.io/docs/posts/supervised_finetuning/</guid><description>&lt;h2 id="the-power-of-supervised-fine-tuning-in-large-language-models-an-in-depth-analysis"&gt;&lt;strong&gt;The Power of Supervised Fine-Tuning in Large Language Models: An In-depth Analysis&lt;/strong&gt;&lt;a class="anchor" href="#the-power-of-supervised-fine-tuning-in-large-language-models-an-in-depth-analysis"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;h3 id="introduction"&gt;&lt;strong&gt;Introduction&lt;/strong&gt;&lt;a class="anchor" href="#introduction"&gt;#&lt;/a&gt;&lt;/h3&gt;
&lt;p&gt;In recent years, the development of machine learning, particularly large language models (LLMs), has revolutionized the way we approach a multitude of challenges, from query-based tasks to content generation. In this post, we will dive deep into a technique gaining traction within the AI community - supervised fine-tuning using domain-specific instruction datasets - and contrast it with the more conventional prompt tuning approach, with a focus on techniques such as retrieval augmentation.&lt;/p&gt;</description></item></channel></rss>