wzhouad/zephyr-ultrafeedback-hybrid download history

wzhouad/zephyr-ultrafeedback-hybrid is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 59 times (6 in the last 7 days), and 1,294 times in total. It ranks #164,922 among datasets by monthly downloads.

Dataset for Training wzhouad/zephyr-7B-WPO-HB This dataset was curated specifically for training the wzhouad/zephyr-7B-WPO-HB model in a hybrid RL setting. The prompts are sourced from the Ultrafeedback dataset, and the corresponding outputs are as follows: On-Policy Outputs: 5 outputs g

Models trained on zephyr-ultrafeedback-hybrid

1 models list it as training data.

Open wzhouad/zephyr-ultrafeedback-hybrid on Hugging Face

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