nvidia/HelpSteer
Viewer • Updated • 37.1k • 1.56k • 247
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 22.1k • 1.68k -
stanfordnlp/SHP
Viewer • Updated • 386k • 3.46k • 323 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 13.6k • 178 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 893 • 240 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 2.05k • 217 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 7.35k • 324 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 896 • 295 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 6.41k • 133 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 330 • 22 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 124 • 45 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 466 • 118 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 767 • 212 -
allenai/reward-bench
Viewer • Updated • 8.11k • 6.54k • 106 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 13.1k • 440 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 22 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 689 • 221