ModelRefs / Learn Fine-Tuning — AI Learning Pathway
Learn Fine-Tuning — AI Learning Pathway
Adapt foundation models with SFT, LoRA, and DPO. Decide when to fine-tune and ship adapted models safely. A 36-hour advanced path.
Overview
Adapt foundation models with SFT, LoRA, and DPO.
What you will be able to do
- Decide SFT vs. RAG vs. prompting
- Run LoRA / QLoRA fine-tuning
- Apply preference optimization (DPO)
- Evaluate and ship adapters
Pathway phases
- Decide — Fine-tune vs. retrieve vs. prompt.
- Train — LoRA + QLoRA runs.
- Ship — Eval + deploy adapters.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Learn Fine-Tuning — AI Learning Pathway.
Frequently asked questions
What will I learn in Learn Fine-Tuning?
Decide SFT vs. RAG vs. prompting Run LoRA / QLoRA fine-tuning Apply preference optimization (DPO)
How long does Learn Fine-Tuning take?
Approximately 36 hours across 3 phases.
What projects are included?
Domain LoRA Adapter • DPO Alignment Run • Adapter Eval Suite • Adapter Serving