argilla/reward-model-data-falcon
Viewer
•
Updated
•
7.4k
•
27
•
1
DPO Dataset
direct preference optimization related datasets
-
-
jondurbin/gutenberg-dpo-v0.1
Viewer • Updated • 918 • 1.09k • 127 -
ybisk/piqa
Updated • 79.4k • 86 -
Dahoas/rm-hh-rlhf
Viewer • Updated • 89.5k • 253 • 2 -
duxx/distilabel-intel-orca-dpo-pairs-tr
Viewer • Updated • 3.98k • 49 • 6 -
Dahoas/rm_instruct_helpful_preferences
Viewer • Updated • 90.7k • 38 • 4 -
Dahoas/1B_hh_sft_ppo_comparison
Viewer • Updated • 100 • 10 -
abacusai/MetaMath_DPO_FewShot
Viewer • Updated • 395k • 98 • 25 -
abacusai/HellaSwag_DPO_FewShot
Viewer • Updated • 150k • 82 • 8