- Hugging Face
- Free
- Intermediate
The LLM Course
Deep, hands-on foundation for open models: transformers, the Hub, fine-tuning and reasoning models.
Open course : The LLM Course. Opens the provider site in a new tab
Engineers / Advanced
Open-weight models and fine-tuning
Run and tune open models yourself: post-training, preference tuning, and when self-hosting is the right call.
Who it is for
Engineers with Python and PyTorch basics who want to adapt a small open model to their own task.
- Steps
- 8
- Level
- Advanced
What you can do afterwards
- Fine-tune a small open model on your own task
- Compare it with a general model on the same test set
- Judge when self-hosting is worth it
The path, step by step
Course
Course
- Hugging Face
- Free
- Intermediate
smol course (fine-tuning language models)
A practical course on tuning and aligning small language models yourself, with certificates.
Open course : smol course (fine-tuning language models). Opens the provider site in a new tab
Course
- DeepLearning.AI
- Cost not stated
- Intermediate
- 1 h 26 min
Post-training of LLMs
A short post-training overview that pairs with the smol course.
Open course : Post-training of LLMs. Opens the provider site in a new tab
Course
- DeepLearning.AI
- Cost not stated
- Intermediate
- 1 h 53 min
Reinforcement Fine-Tuning LLMs With GRPO
Fine-tuning open-weight models with a reinforcement approach.
Open course : Reinforcement Fine-Tuning LLMs With GRPO. Opens the provider site in a new tab
Build
Fine-tune a small model and compare it
Goal. Tune a small open model on a narrow task and show with numbers whether it beats the untuned model.
What to do
- Pick a narrow task, such as classifying support tickets, and write a test set of 50 examples.
- Score the untuned model on the test set first. That is your baseline.
- Fine-tune on a training set that does not overlap the test set.
- Compare quality, speed and cost per thousand requests.
What good looks like. You can state, with numbers, when the tuned model is the better choice and when it is not.
Read
Posts to read
What drives the cost and latency of serving a model, which decides if self-hosting pays off.
Check
Sovereign AI readiness checklist
The questions to answer before you host a model on your own infrastructure or in a European region.
Check
Guide: API or self-hosted model
A short guide to the trade-offs between calling an API and running a model yourself.
Course details come from each provider. Check the provider page for the latest.
Next path
- Engineers
- Intermediate
LLM apps and RAG
Build an application on a language model: open-model foundations, retrieval, the Claude API and a test set that tells you if it works.
View the pathLearn this with your team
We run workshops for company teams and for students, tailored to your stack.
Learn this with your team
Next step
Want your team to learn this together?
We give workshops to company teams and students, on-site or online. Tell us who the participants are and what they should be able to do afterwards.
Accepting projects for Q4 2026