sounds like post-processing made out to be something more?
everyone is doing this, it's just part of the pipeline, certainly nothing innovative on that front in guidance
everyone is doing this, it's just part of the pipeline, certainly nothing innovative on that front in guidance
The mostly widely accessible form of this is probably BNF grammar biasing in llama.cpp: https://github.com/ggerganov/llama.cpp/blob/master/grammars/...