<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>NLP | Gabriel Humpire-Mamani</title><link>https://gabrielhumpire.github.io/tags/nlp/</link><atom:link href="https://gabrielhumpire.github.io/tags/nlp/index.xml" rel="self" type="application/rss+xml"/><description>NLP</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sat, 26 Jul 2025 00:00:00 +0000</lastBuildDate><image><url>https://gabrielhumpire.github.io/media/icon_hu_645fa481986063ef.png</url><title>NLP</title><link>https://gabrielhumpire.github.io/tags/nlp/</link></image><item><title>LLM Fine-tuning &amp; RAG Pipelines</title><link>https://gabrielhumpire.github.io/project/llm/</link><pubDate>Sat, 26 Jul 2025 00:00:00 +0000</pubDate><guid>https://gabrielhumpire.github.io/project/llm/</guid><description>&lt;p&gt;Fine-tuning large language models using LoRA and QLoRA for domain-specific tasks, with retrieval-augmented generation (RAG) pipelines for grounded outputs. Evaluated and refined LLM-generated Python and C++ code through systematic quality assessment loops.&lt;/p&gt;</description></item></channel></rss>