AI & ML — FINE-TUNING & MODEL TRAINING

Fine-tuning & Model Training

Most topics here have three levels — Introduction, Intermediate, and Advanced — so pick one and go as deep as you want. A few go straight to Intermediate for readers who already have the basics down.

Fine-tuning Basics
When updating a model’s actual weights beats prompting or RAG — and the real trade-offs once it goes into production.
Intermediate Advanced
LoRA & Parameter-Efficient Fine-tuning
Freezing the original model and training small adapter matrices instead — why that’s dramatically cheaper, and how far it can be pushed.
Intermediate Advanced
RLHF & Preference Tuning
Teaching a model what humans actually prefer — the real RLHF pipeline, and DPO as a simpler modern alternative.
Intermediate Advanced