nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
1.83k
•
231
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 13.5k • 1.27k -
stanfordnlp/SHP
Viewer • Updated • 386k • 1.85k • 297 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 3.4k • 125 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 525 • 229 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.57k • 196 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 8.11k • 267 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 800 • 286 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 1.77k • 129 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 528 • 18 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 217 • 44 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 522 • 107 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 1.27k • 204 -
allenai/reward-bench
Viewer • Updated • 8.11k • 9.76k • 87 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 12.8k • 401 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 33 • 6 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 530 • 221