wzhouad/llama3-ultrafeedback-hybrid-v2 download history

wzhouad/llama3-ultrafeedback-hybrid-v2 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 63 times (15 in the last 7 days), and 1,225 times in total. It ranks #157,534 among datasets by monthly downloads.

Dataset for Training wzhouad/Llama3-Instruct-8B-WPO-HB-v2 This dataset was curated specifically for training the wzhouad/Llama3-Instruct-8B-WPO-HB-v2 model in a hybrid RL setting. The prompts are sourced from the Ultrafeedback dataset, and the corresponding outputs are as follows: On-Pol

Models trained on llama3-ultrafeedback-hybrid-v2

1 models list it as training data.

Open wzhouad/llama3-ultrafeedback-hybrid-v2 on Hugging Face

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