nvidia/HelpSteer
Viewer • Updated • 37.1k • 1.87k • 247
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 35.7k • 1.71k -
stanfordnlp/SHP
Viewer • Updated • 386k • 2.65k • 323 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 15k • 181 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 546 • 242 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.84k • 218 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 12.2k • 329 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 992 • 295 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 7.31k • 133 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 385 • 23 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 112 • 45 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 677 • 118 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 422 • 212 -
allenai/reward-bench
Viewer • Updated • 8.11k • 7.78k • 106 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 3.45k • 443 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 13 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 856 • 221