Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

Fine-Tuning with QLoRA

University of Kansas School of Business

When RAG isn’t enough — when you need the model to learn a new style, tone, or core knowledge — you fine-tune it. QLoRA (Quantized Low-Rank Adaptation) makes this possible on a free Colab T4 GPU by:

This chapter fine-tunes a small model on fictional company data and shows a side-by-side before/after comparison.