<?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>Build &amp; Train Models on A.Asonitis</title><link>https://aadonis-ai.github.io/notebook/build-and-train/</link><description>Recent content in Build &amp; Train Models on A.Asonitis</description><generator>Hugo -- 0.157.0</generator><language>en-us</language><lastBuildDate>Fri, 03 Oct 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://aadonis-ai.github.io/notebook/build-and-train/index.xml" rel="self" type="application/rss+xml"/><item><title>HuggingFace Trainer: Custom LLaMA Training</title><link>https://aadonis-ai.github.io/notebook/build-and-train/hf-trainer/</link><pubDate>Fri, 03 Oct 2025 00:00:00 +0000</pubDate><guid>https://aadonis-ai.github.io/notebook/build-and-train/hf-trainer/</guid><description>A complete training script for LLaMA (250M–8B) with a custom tokenizer, label masking, gradient checkpointing, and multi-GPU support via Accelerate.</description></item><item><title>Custom Tokenizer for Audio LLMs</title><link>https://aadonis-ai.github.io/notebook/build-and-train/custom-tokenizer/</link><pubDate>Thu, 02 Oct 2025 00:00:00 +0000</pubDate><guid>https://aadonis-ai.github.io/notebook/build-and-train/custom-tokenizer/</guid><description>Building a HuggingFace-compatible tokenizer for neural audio codec tokens — vocabulary design, special tokens, and uploading to the Hub.</description></item><item><title>HPC Clusters</title><link>https://aadonis-ai.github.io/notebook/build-and-train/hpc-clusters/</link><pubDate>Wed, 01 Oct 2025 00:00:00 +0000</pubDate><guid>https://aadonis-ai.github.io/notebook/build-and-train/hpc-clusters/</guid><description>Redirecting pip, HuggingFace, and PyTorch caches to scratch storage to avoid filling your home directory on shared clusters.</description></item></channel></rss>