nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
1.52k
•
237
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 13.4k • 1.38k -
stanfordnlp/SHP
Viewer • Updated • 386k • 2.53k • 311 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 3.26k • 143 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 509 • 234 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.41k • 209 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 5.05k • 297 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 806 • 291 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 1.75k • 132 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 329 • 21 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 150 • 44 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 391 • 114 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 649 • 207 -
allenai/reward-bench
Viewer • Updated • 8.11k • 3.59k • 97 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 1.86k • 419 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 9 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 424 • 221