nvidia/HelpSteer
Viewer • Updated • 37.1k • 1.82k • 249
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 34.6k • 1.78k -
stanfordnlp/SHP
Viewer • Updated • 386k • 2.84k • 323 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 13k • 187 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 508 • 241 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.63k • 220 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 14.3k • 340 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 1.4k • 295 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 15.3k • 133 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 990 • 24 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 255 • 46 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 781 • 120 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 728 • 214 -
allenai/reward-bench
Viewer • Updated • 8.11k • 5.45k • 107 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 4.61k • 452 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 9 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 576 • 222