GEN-04 · Advanced
Fine-tuning, small language models and model serving
When and how to fine-tune: datasets, LoRA and QLoRA on one GPU, small models for low cost and the edge, quantisation and serving with vLLM, and evaluating the result.
- Self-study hours
- 32
- Class hours
- 20 (7 at beginner depth)
- Lessons
- 10
- Free certifications
- 0
- Library resources
- 8
✓ All 10 lessons expert reviewed
What you will be able to do
- Decide when fine-tuning beats prompting and RAG, with evidence
- Fine-tune a small open model with LoRA or QLoRA on a single GPU
- Quantise and serve a model, and compare its cost with a hosted API
Sign up free to see the lessons, project and free certifications
It takes a minute with your email. AiTeky Pass (₹999/month or ₹9,999/year) is free for your first 30 days.