nvidia/HelpSteer
Viewer • Updated • 37.1k • 2.33k • 253
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 28.9k • 2.4k -
stanfordnlp/SHP
Viewer • Updated • 386k • 3.05k • 325 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 14.1k • 198 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 601 • 242 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 2.28k • 222 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 18.2k • 348 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 1.54k • 299 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 6.76k • 136 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 573 • 26 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 405 • 46 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 813 • 120 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 853 • 214 -
allenai/reward-bench
Viewer • Updated • 8.11k • 11.3k • 110 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 50k • 456 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 50 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 2.01k • 221