nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
1.54k
•
237
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 11.2k • 1.37k -
stanfordnlp/SHP
Viewer • Updated • 386k • 2.31k • 309 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 4.11k • 141 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 850 • 234 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.16k • 207 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 11.1k • 297 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 641 • 290 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 2.97k • 132 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 533 • 21 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 312 • 44 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 360 • 114 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 659 • 207 -
allenai/reward-bench
Viewer • Updated • 8.11k • 5.49k • 95 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 2k • 419 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 9 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 662 • 221