nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
2.25k
•
223
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 9.69k • 1.21k -
stanfordnlp/SHP
Viewer • Updated • 386k • 1.7k • 295 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 3.87k • 120 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 400 • 226 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.19k • 189 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 6.91k • 246 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 464 • 277 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 1.26k • 123 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 432 • 16 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 346 • 43 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 669 • 107 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 1.37k • 199 -
allenai/reward-bench
Viewer • Updated • 8.11k • 7.14k • 77 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 5.84k • 376 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 39 • 6 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 345 • 216