nvidia/HelpSteer
Viewer
•
Updated
•
37.1k
•
1.71k
•
229
Reward Modeling Datasets
-
-
Anthropic/hh-rlhf
Viewer • Updated • 169k • 8.85k • 1.24k -
stanfordnlp/SHP
Viewer • Updated • 386k • 1.23k • 295 -
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 3.24k • 120 -
openai/webgpt_comparisons
Viewer • Updated • 19.6k • 315 • 228 -
openai/summarize_from_feedback
Viewer • Updated • 194k • 922 • 189 -
HuggingFaceH4/ultrafeedback_binarized
Viewer • Updated • 187k • 6.63k • 259 -
berkeley-nest/Nectar
Viewer • Updated • 183k • 295 • 282 -
HuggingFaceH4/stack-exchange-preferences
Viewer • Updated • 10.8M • 1.07k • 128 -
HuggingFaceH4/hhh_alignment
Viewer • Updated • 221 • 135 • 18 -
Birchlabs/openai-prm800k-stepwise-critic
Viewer • Updated • 1.09M • 182 • 43 -
prometheus-eval/Feedback-Collection
Viewer • Updated • 100k • 443 • 107 -
argilla/OpenHermesPreferences
Viewer • Updated • 989k • 665 • 202 -
allenai/reward-bench
Viewer • Updated • 8.11k • 5.38k • 81 -
nvidia/HelpSteer2
Viewer • Updated • 21.4k • 15.2k • 392 -
Magpie-Align/Magpie-Pro-DPO-200K
Viewer • Updated • 207k • 34 • 6 -
argilla/magpie-ultra-v0.1
Viewer • Updated • 50k • 331 • 218