nvidia/HelpSteer
Viewer • Updated • 37.1k • 2.65k • 252
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 38.1k • 2.06k -
stanfordnlp/SHP
Viewer • Updated • 386k • 6.94k • 324 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 10.8k • 196 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 887 • 241 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 2.21k • 220 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 24.3k • 347 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 1.11k • 297 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 10.7k • 135 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 380 • 26 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 214 • 46 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 581 • 120 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 864 • 214 -
allenai/reward-bench
Viewer • Updated • 8.11k • 9.41k • 109 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 181k • 456 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 20 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 2.3k • 221