DtYXs/qwen2.5-7b-ultrafeedback-armorm-binarized download history

DtYXs/qwen2.5-7b-ultrafeedback-armorm-binarized is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 25 times (3 in the last 7 days), and 568 times in total. It ranks #316,473 among datasets by monthly downloads.

This repository contains the data for the paper Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model. Github: https://github.com/DtYXs/Pre-DPO

Open DtYXs/qwen2.5-7b-ultrafeedback-armorm-binarized on Hugging Face

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