Ahjeong/SHP_filtered_MMPO download history
Ahjeong/SHP_filtered_MMPO is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 47 times (15 in the last 7 days), and 1,156 times in total. It ranks #278,802 among datasets by monthly downloads.
Dataset Card for "shp_filtered_MMPO" This is the filtered version of SHP dataset, which was used to train MMPO, as introduced in the paper below: Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback Kyuyoung Kim*, Ah Jeong Seo*, Hao Liu, Jinwoo Shi
Open Ahjeong/SHP_filtered_MMPO on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.