This is amazing. I don't think I fully understand how it works, but the core of having Jev (or some classifier), generate the words/tokens it's going to output by picking/classifying the words/tokens, is very cool
Where do you see the biggest potential improvement gains?
This is amazing. I don't think I fully understand how it works, but the core of having Jev (or some classifier), generate the words/tokens it's going to output by picking/classifying the words/tokens, is very cool
Where do you see the biggest potential improvement gains?
Really interesting approach. I’m curious how much the verifier pass improves the output quality compared to just increasing the token vocabulary.