nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
1.85k
•
243
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 26.6k • 1.51k -
stanfordnlp/SHP
Viewer • Updated • 386k • 3.86k • 318 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 7.15k • 162 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 9.08k • 237 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.64k • 215 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 8.82k • 316 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 984 • 294 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 3.45k • 133 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 306 • 21 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 127 • 45 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 431 • 115 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 1.43k • 209 -
allenai/reward-bench
Viewer • Updated • 8.11k • 8.93k • 102 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 4.17k • 432 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 14 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 698 • 221