nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
2.01k
•
235
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 13.6k • 1.3k -
stanfordnlp/SHP
Viewer • Updated • 386k • 2.32k • 302 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 5.65k • 130 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 962 • 230 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 2.01k • 199 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 6.38k • 280 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 1.7k • 288 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 3.08k • 131 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 544 • 20 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 109 • 44 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 915 • 112 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 1.07k • 204 -
allenai/reward-bench
Viewer • Updated • 8.11k • 6.93k • 91 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 3.45k • 411 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 16 • 6 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 764 • 222