setzer22

> @Noeda of https://github.com/Noeda/rllama might wanna tag along here :relaxed: > > Also, a Tauri-app equivalent to https://github.com/lencx/ChatGPT would pair very well with this. Good task for anyone who wants...

> I just checked my latest commit and on CPU only OpenCL I got 678ms per token. (with GPU, ~230ms). The llama.cpp project mentions in README.md that they are at...

Yup, sounds good :+1:

Amazing work on llamacord btw! :smile: I'm gonna try this out

> As an aside: should the CLI be llama-cli or llama-rs-cli I was originally thinking llama-rs-cli. But after seeing the name, I really like `llama-cli`, especially if it ends up...

As @philpax already pointed out, the only _legal_ source is facebook, and you have to go through their channels. But it is well known that the weights leaked a few...

It will not be possible to run tests, however, because I don't think we can put the weights on the CI server. But still, something to just verify it compiles...

Hey! Sorry we didn't merge this sooner. Currently this branch has drifted a lot from `main` and CI is enforcing that there are no errors reported by clippy, so the...

I took the liberty to create a discord server :smile: But we can move somewhere else if you folks think there's a better option: https://discord.gg/GBTh6HeG

The discord is now featured in the README, so I think we can close this :smile: