VideoMAEv2 icon indicating copy to clipboard operation
VideoMAEv2 copied to clipboard
verified publisher icon OpenGVLab

Vit_B , Vit_S pretrained weights (not HuggingFace inference one, but also for Decoder)

Open nomaad42 opened this issue 10 months ago • 1 comments

Thank you very much for this awesome repo!

Could you please provide the Vit_b, and Vit_S pretrained pth weights?

In HuggingFace there's only model.safetensors for Encoder part only. It would be awesome

nomaad42 avatar Mar 19 '25 14:03 nomaad42

any update on the availability of the ViT_B and ViT_S weights for the encoder-decoder pre-trained version?

villifCoder559 avatar Jul 22 '25 16:07 villifCoder559