PEFT, LoRA, and QLoRA tutorial roadmap

A tutorial outline for efficient LLM fine-tuning and evaluation.

Tutorial Goal

Explain when fine-tuning is appropriate, how parameter-efficient fine-tuning works, and how to evaluate whether it improves the target task.

Sections To Build

1. Fine-tuning versus prompting versus retrieval.
2. Dataset construction and labeling.
3. PEFT and LoRA concepts.
4. QLoRA for memory-efficient training.
5. Evaluation and regression testing.
6. Deployment and model versioning.

Notebook Plan

• notebooks/lora-fine-tuning/01-data-preparation.ipynb
• notebooks/lora-fine-tuning/02-peft-lora-basics.ipynb
• notebooks/lora-fine-tuning/03-evaluation.ipynb