News for hackers. Stuff that matters.
Re:Building a fully local LLM voice assistant to control my ... by khimaros on Saturday January 13, 2024 @10:32PM (#38987178)
llama.cpp supports custom grammars to constrain inference. maybe this is a helpful starting point? https://github.com/ggerganov/llama.cpp/tree/master/grammars

There are no comments on this comment yet.