Unlocks after Module 10The AI Engineering Program
Module 11: Fine-Tuning, Open Models & Inference
Decide when fine-tuning beats prompting, fine-tune a small open model on free GPUs, and serve it efficiently.
24guided hours
10lessons
11 of 13in the program
Lessons
10 lessons, in order. Each one unlocks when you finish the one before it.
- 11.1Fine-tune, RAG or prompt? A decision framework
- 11.2Dataset engineering and synthetic data
- 11.3LoRA and QLoRA on a free Colab GPU
- 11.4Instruction tuning for structured extraction
- 11.5Preference tuning (DPO): an introduction
- 11.6Evaluating a fine-tune against the prompt baseline
- 11.7Quantisation and running models locally
- 11.8Serving: throughput, latency and cost
- 11.9Publishing a model with a model card on the Hugging Face Hub
- 11.10Module project
Your first lesson is on us.
AI vs ML vs DL vs GenAI: deep notes, a hands-on lab and a quiz. No card. No catch.