nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
2.22k
•
236
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 15.9k • 1.33k -
stanfordnlp/SHP
Viewer • Updated • 386k • 1.89k • 305 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 4.28k • 136 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 549 • 231 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 2.51k • 203 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 8.53k • 284 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 571 • 288 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 3.02k • 132 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 616 • 21 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 136 • 44 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 812 • 112 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 474 • 203 -
allenai/reward-bench
Viewer • Updated • 8.11k • 7.43k • 94 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 4.25k • 412 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 14 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 375 • 221