nvidia/Llama-3.3-Nemotron-70B-Reward-Principle
Text Generation
•
71B
•
Updated
•
877
•
2
Reward Models 10-2025
A collection of great reward models for research and production
-
-
nvidia/Qwen3-Nemotron-32B-GenRM-Principle
Text Generation • 33B • Updated • 112 • 6 -
nvidia/Qwen3-Nemotron-32B-RLBFF
Text Generation • 33B • Updated • 940 • 25 -
nvidia/Qwen3-Nemotron-8B-BRRM
Text Generation • Updated • 139 • 4 -
nvidia/Qwen3-Nemotron-14B-BRRM
Text Generation • Updated • 65 • 5 -
RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
Paper • 2509.21319 • Published • 4