nvidia/Llama-3.3-Nemotron-70B-Reward-Principle
Text Generation • 71B • Updated • 296 • 7
Reward Models 10-2025
A collection of great reward models for research and production
-
-
nvidia/Qwen3-Nemotron-32B-GenRM-Principle
Text Generation • 33B • Updated • 1.05k • • 17 -
nvidia/Qwen3-Nemotron-32B-RLBFF
Text Generation • 33B • Updated • 242 • • 28 -
nvidia/Qwen3-Nemotron-8B-BRRM
Text Generation • Updated • 1.48k • • 9 -
nvidia/Qwen3-Nemotron-14B-BRRM
Updated • 1.21k • 13 -
RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
Paper • 2509.21319 • Published • 10 -
nvidia/HelpSteer3
Viewer • Updated • 133k • 9.71k • 110