Hacker News new | ask | show | jobs
by adeon 1178 days ago
This looks really good for a run-it-on-your-own-hardware model from the examples and sibling comments. I've been working on a pure AVX2 Rust implementation of LLaMA but was starting to lose interest and been waiting for whatever is the next hot downloadable model, but now I want to add this thing to it.

I'll be busy next few days. Heck yeah.

1 comments

Are you the GGML dev?
No, my project is called rllama. No relation to GGML. https://github.com/Noeda/rllama