Running
Exam 1 - Fundamentals of GRPO
🔥
Test your knowledge of GRPO, TRL, RL, and Deepseek R1.
Hugging Face Reasoning Course
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
The Reasoning Course
Welcome to the Hugging Face Reasoning Course! This is a specific cohort of the Hugging Face NLP Course, which focuses on fine-tuning models for reasoning abilities.
We are exploring Open R1, a groundbreaking community project that's making advanced AI accessible to everyone. Specifically, this course is to help students and learners to use Open R1 in their own projects. Any maybe even contribute to the community project!
Next releases
| Date | Unit |
|---|---|
| March 7th, 2025 | No-Code Exam and Certification |
| March 14th, 2025 | Next Practical Exercise |
| March 21st, 2025 | Interactive code review |
| March 2025 | Unsloth exercise on fine-tuning a model with GRPO |
| April 2025 | More written material on building reasoning models |
| April 2025 | Live sessions on building Open R1 |
| April 2025 | Code Exam and Certification |