ys-zong/VLGuard download history

ys-zong/VLGuard is an image to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 313 times (59 in the last 7 days), and 5,949 times in total. It ranks #47,497 among datasets by monthly downloads.

VLGuard [Website] [Paper] [Code] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models. (ICML 2024) Dataset We host VLGuard dataset here. train.json and test.json are the meta data of VLGuard and the images are in train.zip and test.zip. U

Models trained on VLGuard

1 models list it as training data.

• Foreshhh/Qwen2-VL-7B-VLGuard 41 downloads in 30 days

Open ys-zong/VLGuard on Hugging Face

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