YDXX/G-Health-dpo-data download history

YDXX/G-Health-dpo-data is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 8 times (2 in the last 7 days), and 561 times in total. It ranks #637,263 among datasets by monthly downloads.

G-Health DPO Data This directory contains the Direct Preference Optimization (DPO) dialogue data used in Stage 2 of the G-Health model training pipeline. Overview In Stage 2, our goal is to maximally strengthen the model's preference for correct answers. To this end, we

Open YDXX/G-Health-dpo-data on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.