News for hackers. Stuff that matters.
Re:LLaMA Now Goes Faster on CPUs by Eisenstein on Monday April 01, 2024 @10:58PM (#39901949)
Llava just integrates Clip with a llama model. Koboldcpp can now do this with many models out of the box:

* https://github.com/LostRuins/koboldcpp/releases/tag/v1.61.2

There are no comments on this comment yet.