<?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>Deep-Learning on Jeswanth's Blog</title><link>https://jeswanthmukesh20.github.io/tags/deep-learning/</link><description>Recent content in Deep-Learning on Jeswanth's Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 04 Jun 2026 19:36:59 +0530</lastBuildDate><atom:link href="https://jeswanthmukesh20.github.io/tags/deep-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>RoPE Implementation Explained Mathematically</title><link>https://jeswanthmukesh20.github.io/posts/rope-from-scratch/</link><pubDate>Thu, 04 Jun 2026 19:36:59 +0530</pubDate><guid>https://jeswanthmukesh20.github.io/posts/rope-from-scratch/</guid><description>A detailed mathematical walkthrough of Rotary Position Embedding (RoPE) as implemented in HuggingFace&amp;#39;s Llama model, covering inverse frequencies, rotation matrices, and the relative position property.</description></item></channel></rss>