Adapt a model without wrecking it
Fine-tuning and Customisation
When to fine-tune, data preparation, LoRA and QLoRA mathematics, preference tuning, distillation, merging, evaluating a fine-tune and serving adapters, with a runnable LoRA demonstration.
1 tracks · 4 lessons · about 1 hours · 1 free lessons · 0 animated diagrams
What you will be able to do
- ✓Decide between prompting, RAG and fine-tuning with evidence
- ✓Prepare, deduplicate and split training data safely
- ✓Explain LoRA rank, alpha and memory costs with numbers
- ✓Evaluate and serve a fine-tuned model responsibly
Who it is for
Builders deciding whether and how to customise a model.
Prerequisites
Local LLM Inference basics; the Evaluation course is recommended.
Curriculum
Fine-tuning Foundations
IntermediateWhen to fine-tune, data preparation, preference tuning, distillation, merging, evaluating and serving adapters.