nvidia/Nemotron-4-340B-Reward
Updated
•
34
•
125
Reward Models
NVIDIA Nemotron reward models: 340B, 8B BRRM, 70B/32B principle-based. RLHF training, preference learning, AI alignment research.
-
-
nvidia/Qwen3-Nemotron-8B-BRRM
Text Generation • Updated • 724 • 8 -
nvidia/Llama-3.3-Nemotron-70B-Reward-Principle
Text Generation • 71B • Updated • 85 • 5 -
nvidia/Qwen3-Nemotron-32B-GenRM-Principle
Text Generation • 33B • Updated • 838 • 11 -
nvidia/Qwen3-Nemotron-32B-RLBFF
Text Generation • 33B • Updated • 122 • 27 -
nvidia/Qwen3-Nemotron-14B-BRRM
Text Generation • Updated • 209 • 11 -
nvidia/HelpSteer3
Viewer • Updated • 133k • 2.62k • 93