<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM on funinkina's corner</title><link>https://funinkina.co.in/tags/llm/</link><description>Recent content in LLM on funinkina's corner</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 28 Mar 2025 20:37:57 +0530</lastBuildDate><atom:link href="https://funinkina.co.in/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Query MD</title><link>https://funinkina.co.in/projects/query-md/</link><pubDate>Fri, 28 Mar 2025 20:37:57 +0530</pubDate><guid>https://funinkina.co.in/projects/query-md/</guid><description>&lt;p&gt;QueryMD is an AI-powered application designed to help users interact with and query their personal markdown notes. It allows you to ask questions and search your notes using natural language, leveraging the power of large language models.&lt;/p&gt;
&lt;h3 id="github-repository-funinkinaquerymd"&gt;GitHub Repository: &lt;a href="https://github.com/funinkina/QueryMD" target="_blank" rel="noreferrer nofollow"&gt;funinkina/QueryMD&lt;/a&gt;
&lt;/h3&gt;
&lt;p&gt;&lt;img src="https://github.com/funinkina/QueryMD/raw/main/Screenshot.png" alt="Screenshot" loading="lazy"&gt;&lt;/p&gt;
&lt;h2 id="main-usage-of-this"&gt;Main usage of this?&lt;/h2&gt;
&lt;p&gt;If you are like me, who writes all their notes using markdown that is locally stored, this tool will be super handy. I use it frequently to manage and search some obscure reference I wrote somewhere.&lt;/p&gt;</description></item><item><title>Running Deepseek on Raspberry Pi</title><link>https://funinkina.co.in/blog/running-deepseek-on-raspberry-pi/</link><pubDate>Fri, 31 Jan 2025 23:42:36 +0530</pubDate><guid>https://funinkina.co.in/blog/running-deepseek-on-raspberry-pi/</guid><description>&lt;p&gt;Let&amp;rsquo;s start by addressing the elephant in the room, why? Why would I run a freaking Large Language Model on a 4-core arm processor with 4GB of RAM? Well, why not? I have a Raspberry Pi 4 lying around and I wanted to see if I could run Deepseek on it. (Also cause free content for the blog). Before starting, let me say, I have absolutely zero expectations from this experiment. I am not expecting it to work, I am not expecting it to be fast, I am not expecting it to be usable. I am just doing it because I can. So, let&amp;rsquo;s get started.&lt;/p&gt;</description></item></channel></rss>