Fine-Tuning & LoRA

Customize models with LoRA, QLoRA, Unsloth, and Axolotl — fine-tune 70B models on a single GPU. Part of the free Open Source AI Academy — every lesson below is open to everyone, no signup required.

// LESSONS IN THIS MODULE

1. 01LoRA & QLoRA Explained15 min · 150 XP

   Parameter-Efficient Fine-Tuning (PEFT) Full fine-tuning updates all billions of parameters — requiring massive GPU clusters. PEFT freezes the base mod...