You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
It seems that the output of the smallest distilled model is 512 dimensional. How does that work with the text encoder that gives back a 1024 dimensional vector?
Is there any chance you could upload the state_dict rather than jit files? Thanks
The text was updated successfully, but these errors were encountered: