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
I finetuned text encoder of CLIP and added some additional tokens to it, I would like to know is there a way to load the checkpoint with greater embedding size?
The text was updated successfully, but these errors were encountered:
don't think resizing existing models is practical, but definitely possible to make new ones, or us HF pretrained models that have larger vocab / context length
I finetuned text encoder of CLIP and added some additional tokens to it, I would like to know is there a way to load the checkpoint with greater embedding size?
The text was updated successfully, but these errors were encountered: