So in theory you could feed it incomplete text, and then ask it for the probabilities of what the next character could be?
Or a partially completed song, asking for the next note. I’m not sure if you’re joking, but using it for space constrained next token generation within a grammar sounds like a really neat use case.
you could, but it the model is not optimized for text
this is complex, but generating text is highly complicated and requires mode dropping to make long cohesive text
If you provide it an AST of the english language, yes.
was wondering same
I think the joke here is getting missed