The AI Engineering Program: Module 11 of 13
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
Onlineself-paced
Lessons
Every lesson: deep notes, curated lectures, an animated explainer, a hands-on lab, practice questions and a timed exam.
- Fine-tune, RAG or prompt? A decision framework
- Dataset engineering and synthetic data
- LoRA and QLoRA on a free Colab GPU
- Instruction tuning for structured extraction
- Preference tuning (DPO): an introduction
- Evaluating a fine-tune against the prompt baseline
- Quantisation and running models locally
- Serving: throughput, latency and cost
- Publishing a model with a model card on the Hugging Face Hub
- Module project
Tools introduced: LoRA fine-tuning
Module project
Fine-tune a small open model to extract fields from Indian documents, beat the prompt-only baseline on a held-out eval set, and publish it on the Hugging Face Hub.