nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
2.33k
•
222
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 9.37k • 1.21k -
stanfordnlp/SHP
Viewer • Updated • 386k • 1.56k • 295 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 3.75k • 119 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 409 • 226 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.2k • 188 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 6.49k • 245 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 488 • 277 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 1.23k • 122 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 379 • 16 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 327 • 43 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 666 • 107 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 1.79k • 199 -
allenai/reward-bench
Viewer • Updated • 8.11k • 6.89k • 75 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 12.4k • 374 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 39 • 5 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 412 • 217