Pure Image input supported if we only want to evaluate the harmfulness of the image ?

#13
by Foreshhh - opened

Pure Image input supported if we only want to evaluate the harmfulness of the image ?

want to know this too

Having same question.

From the paper (chapter 6):

Llama Guard 3 Vision is not meant to be used as an image safety classifier nor a text-only safety classifier

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment