nvidia/HelpSteer
Viewer
• Updated
• 37.1k • 4.93k • 246
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 17.6k • 1.66k -
stanfordnlp/SHP
Viewer • Updated • 386k • 2.37k • 322 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 8.52k • 177 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 388 • 240 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 5.59k • 217 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 5.16k • 323 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 1.1k • 295 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 3.87k • 133 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 157 • 22 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 78 • 45 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 404 • 118 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 512 • 211 -
allenai/reward-bench
Viewer • Updated • 8.11k • 5.68k • 105 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 15.4k • 439 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 7 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 283 • 221