Comment by skerit
13 hours ago
So in theory you could feed it incomplete text, and then ask it for the probabilities of what the next character could be?
13 hours ago
So in theory you could feed it incomplete text, and then ask it for the probabilities of what the next character could be?
I think the joke here is getting missed
Strings trigger us
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.
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.
Feed the generated note back into the input for the next query and you have ... autoregression?
was wondering same