Editorial Notice: This is a public profile curated by AlsoClick based on publicly available educational content and research. Are you Leandro von Werra?
Claim This Profile →Leandro von Werra
Discovered Profile • UnclaimedClaim profile →
Creator of TRL (Transformer Reinforcement Learning) at Hugging Face
About
Leandro von Werra is an ML engineer at Hugging Face who created the TRL library for fine-tuning language models with RLHF and DPO, powering thousands of community models.
Focus Areas & Expertise
RLHFDPOTRLAlignmentReinforcement Learning
Follow Leandro von Werra
Explore their latest content and experiments directly on their channels.
Visit github →