Home/Models/nemotron-4-340b-reward
LLMOpen SourceOpen SourceAlignment

Nemotron-4 340B Reward

by NVIDIA · Open reward model for RLHF.

Visit website ↗
RAI ScoreB+Solid
800/ 1000
↑ 72RAI7dMethodology
Composite of 8 signals · 2,481 contributors

// Live community signal

Rate this model

4
RAI · live
Sign in to cast your signal →

About

NVIDIA's open reward model used for synthetic data and alignment pipelines.

Dimension Scores

intelligence96
creativity88
accuracy94
speed72
coding98
research92
value84
safety90

Pros

  • +Open weights
  • +Strong RLHF signal
  • +Permissive license

Cons

  • Niche use case
  • Heavy compute

Community Reviews

Reviews open once this model is indexed in the live database.

Similar AIs