TIGER-Lab/VISTA-VideoLLaVA download history
TIGER-Lab/VISTA-VideoLLaVA is a 7.4B-parameter video text to text model by TIGER-Lab. In the last 30 days it was downloaded 35 times (15 in the last 7 days), and 232 times in total.
It ranks #336,643 on the Hub by monthly downloads and #283 among video text to text models.
It has 0 likes.
Open TIGER-Lab/VISTA-VideoLLaVA on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.