Model Architectures · Practitioner
Practical Fine-Tuning with LoRA and PEFT
Run a real parameter-efficient fine-tune: dataset design, LoRA hyperparameters, QLoRA, evaluation, and adapter deployment.
- 1 hours lesson
- advanced level
- Engineering Track
- Narrated presentation
What you’ll learn
- Low-rank adaptation and frozen base weights
- Dataset curation, formatting, and leakage checks
- Rank, alpha, and target module selection
- QLoRA and 4-bit base quantisation
- Catastrophic forgetting checks
- Adapter versioning and hot-swap serving
Inside this lesson
A narrated, slide-by-slide presentation with 1 prediction exercise, 1 knowledge check, 4 videos. You answer as you go, and the platform checks your work.