nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
1.74k
•
230
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 8.87k • 1.26k -
stanfordnlp/SHP
Viewer • Updated • 386k • 1.66k • 296 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 2.7k • 123 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 400 • 228 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 1.07k • 193 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 8.31k • 266 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 650 • 285 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 1.82k • 128 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 361 • 18 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 214 • 43 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 516 • 108 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 1.27k • 203 -
allenai/reward-bench
Viewer • Updated • 8.11k • 7.71k • 83 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 15.8k • 399 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 40 • 6 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 442 • 219