Make a model follow the behavior you need.
Use one real tiny GPT to study training data, SFT, LoRA and QLoRA, DPO, distillation, quantization, and the decision to fine-tune at all.
What you will leave with
You can choose an adaptation method, prepare the data and objective, measure the result, and carry the same reasoning to larger models.
What you will be able to do
The curriculum is organized around these 4 practical outcomes.
Decide when fine-tuning is justified
Prepare clean instruction and preference data
Implement SFT, LoRA, and DPO objectives
Evaluate distillation and quantization tradeoffs
Course map
Curriculum
Open a module to inspect every section before you start. Your progress follows you through the course.
context, system controls, and weights, prompt / few-shot / RAG / fine-tune, InstructGPT: 1.3B beat 175B, and more.
training examples, special tokens, data failure modes, and more.
supervised fine-tuning, loss masking, overfitting, and more.
low-rank adapters, rank & alpha, merging, and more.
preference pairs, RLHF, DPO, and more.
deploy math, soft targets, distillation temperature, and more.
merge & export, int8 quantization, serving math, and more.
the method ladder, decision tree, known limits, and more.
Who this course is for
Start with the background you have. The prerequisite notes above tell you exactly what is assumed.
AI engineers evaluating fine-tuning
ML practitioners moving into post-training
Teams comparing prompting, RAG, and weight updates
Continue learning
Each course stands on its own. Pick the one closest to the next task you need to handle.
Engineer what the model sees and returns.
Turn one LLM call into a dependable service.
Replace “it feels better” with evidence.
Start the course
Module 1 introduces the language and example used throughout the rest of the course.
