We train this teacher primarily using RLHF.
4 more from this model
Super’s post-training pipeline combines supervised fine-tuning, Reinforcement Learning from Verifiable Rewards (RLVR), Reinforcement Learning from Human Feedback (RLHF)
Reinforcement learning with verifiable rewards, reinforcement learning from human feedback, and specialized teacher training
Reinforcement Learning from Human Feedback (RLHF)
reinforcement learning from human feedback