Does this model have CLS token?

#6
by risakri001 - opened

Hello,
The video embeddings for this model are coming shape of torch.Size([1, 10240, 1024]). So, does it have a CLS token to get global embeddings, or do we need to take the mean of all the tokens to get the global embedding of the entire video?
Thanks.

AI at Meta org

Hey @risakri001 , there is no cls token in V-JEPA 2 model

Okay, Thanks for answering.

risakri001 changed discussion status to closed

Sign up or log in to comment