nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
2.7k
•
217
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 8.44k • 1.19k -
stanfordnlp/SHP
Viewer • Updated • 386k • 1.77k • 293 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 3.3k • 114 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 351 • 224 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.17k • 188 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 6.16k • 234 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 575 • 276 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 1.5k • 121 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 223 • 16 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 531 • 43 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 604 • 106 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 4.85k • 198 -
allenai/reward-bench
Viewer • Updated • 8.11k • 7.1k • 73 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 18.6k • 359 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 41 • 5 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 542 • 210