pppop7/LLaVA-Pretrain download history

pppop7/LLaVA-Pretrain is an image to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 10 times (5 in the last 7 days), and 402 times in total. It ranks #569,006 among datasets by monthly downloads.

LLaVA-Pretrain Dataset Pretraining data for LLaVA (Large Language and Vision Assistant). Description This dataset contains the pretraining data used in LLaVA training, including: blip_laion_cc_sbu_558k.json - Annotation file with 558K image-caption pairs images/ - Correspondin

Open pppop7/LLaVA-Pretrain on Hugging Face

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