nvidia/HelpSteer
Viewer • Updated • 37.1k • 2.87k • 252
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 34.7k • 2k -
stanfordnlp/SHP
Viewer • Updated • 386k • 6.37k • 323 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 13.3k • 195 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 810 • 241 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 2.53k • 220 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 20.6k • 345 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 1.08k • 296 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 10.3k • 135 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 483 • 26 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 243 • 46 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 656 • 120 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 652 • 214 -
allenai/reward-bench
Viewer • Updated • 8.11k • 9.95k • 109 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 149k • 454 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 16 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 1.57k • 221