nvidia/HelpSteer
Viewer • Updated • 37.1k • 1.63k • 251
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 36.1k • 1.84k -
stanfordnlp/SHP
Viewer • Updated • 386k • 2.83k • 323 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 17.9k • 192 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 969 • 241 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 2.49k • 220 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 18k • 344 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 915 • 296 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 6.17k • 133 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 630 • 26 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 219 • 46 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 745 • 120 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 617 • 214 -
allenai/reward-bench
Viewer • Updated • 8.11k • 7.73k • 109 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 8.34k • 454 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 11 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 940 • 221