Has many followers (331); contributed to the development of several popular GitHub projects, including but not limited to:
- open-r1
- trl
- alignment-handbook
- godot_rl_agents
- sample-factory
Research Experience
Works as a Research Scientist at Hugging Face; involved in several open-source projects such as open-r1 (fully open reproduction of DeepSeek-R1), trl (train transformer language models with reinforcement learning), and alignment-handbook (robust recipes to align language models with human and AI preferences).