- Home
- Guides and documents
- a smol course
a smol course
Hands-on course on fine-tuning and aligning small language models
What it is
A practical Hugging Face course on adapting small language models to a specific use case, built around SmolLM3. Units cover instruction tuning, evaluation, preference alignment, vision language models and more, with exercises and a leaderboard. It is designed to run on modest local hardware without paid services.
Good for
- Fine-tune a small model on your own data
- Evaluate a model on a custom domain
- Learn preference alignment methods
What you need
Python; a local GPU or Apple Silicon helps; free Hugging Face account
Sources
- https://github.com/huggingface/smol-course (project README, read 11 Nov 2026)
- https://api.github.com/repos/huggingface/smol-course (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.