nvidia/HelpSteer
Viewer • Updated • 37.1k • 2.59k • 248
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 39.9k • 1.74k -
stanfordnlp/SHP
Viewer • Updated • 386k • 2.93k • 323 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 14.8k • 184 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 1.22k • 242 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 2.38k • 220 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 17k • 338 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 1.12k • 295 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 14.9k • 133 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 685 • 24 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 236 • 46 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 1.14k • 120 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 974 • 214 -
allenai/reward-bench
Viewer • Updated • 8.11k • 8.36k • 107 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 5.3k • 452 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 14 • 7 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 948 • 222