RLVER Checkpoints trained via RLVER, the first RLVR framework to boost LLM empathy. RLVER/PPO-non-thinking 8B • Updated Jul 9 • 6 • 1 RLVER/GRPO-thinking 8B • Updated Jul 9 • 4 RLVER/PPO-thinking 8B • Updated Jul 9 • 4 RLVER/GRPO-non-thinking 8B • Updated Jul 9 • 8
RLVER Checkpoints trained via RLVER, the first RLVR framework to boost LLM empathy. RLVER/PPO-non-thinking 8B • Updated Jul 9 • 6 • 1 RLVER/GRPO-thinking 8B • Updated Jul 9 • 4 RLVER/PPO-thinking 8B • Updated Jul 9 • 4 RLVER/GRPO-non-thinking 8B • Updated Jul 9 • 8
