Archive
Fine-Tuning & Training

The HuggingFace Fine-Tuning Library

Archive
Easy
100pts0 solves
HuggingFace's library for transformer reinforcement learning — implementing PPO, DPO, GRPO, KTO, and ORPO — goes by which three-letter name?
Show hint
T + R + L. The L is 'Learning'.

Archive — no submissions accepted

This challenge is preserved for reference. Play live challenges at /challenges.