Course
Fine-Tuning
Adapting pretrained models with supervised and preference methods.
L3 · AdvancedFast-movingKnown~3 h
What you’ll learn
- Decide when fine-tuning is the right tool versus prompting or RAG
- Explain supervised fine-tuning, instruction tuning, and preference optimization
- Use LoRA and QLoRA and avoid the common data and training pitfalls
Prerequisites
llm-foundations
Module 1. When & How
Deciding to fine-tune, SFT, and preference optimization.
Module 2. Efficient Fine-Tuning
LoRA, QLoRA, and the data that decides success.