nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
1.87k
•
240
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 17.3k • 1.39k -
stanfordnlp/SHP
Viewer • Updated • 386k • 3.46k • 314 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 3.72k • 146 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 746 • 236 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.66k • 213 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 9.91k • 299 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 269 • 291 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 1.16k • 132 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 943 • 21 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 50 • 44 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 424 • 115 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 423 • 208 -
allenai/reward-bench
Viewer • Updated • 8.11k • 10.6k • 98 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 2.63k • 421 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 8 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 413 • 221