marin-community/marin-8b-instruct Text Generation • 8B • Updated May 19, 2025 • 1.82k • • 27
Running 593 Scaling test-time compute đŸ“ˆ 593 Boost LLM answers with search‑guided test‑time compute
Reward models on the hub Collection UNMAINTAINED: See RewardBench... A place to collect reward models, an often not released artifact of RLHF. • 18 items • Updated Apr 13, 2024 • 25