Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
cafkafk 
posted an update 5 days ago
Post
4464
I'm working on a local model that can be run on stuff like an an RTX 3080 at 60 t/s. I'm focused on making it good at Rust and Nix. It's... not done yet, but doing great already. Had a 28/100 on livebench v6 earlier, which obviously isn't amazing.

But for my first real model, very exciting. Can't wait to share more as I get closer to the finish line in the coming weeks.

Really looking forward to it!!!

Great goal! I'm also trying something like that, but more as an SFT for fine-tuning. But now I've pivoted to a sophisticated library inside my coding-agent...

keep going bro, once you make one trust me its hard to stop!

·

The only barrier so far will be getting enough compute in the future. But yes, it's honestly super addictive!

Thats cool! If you can say, how big is the model, im curious

·

32B-A3.4B but that may change slightly as I finish training it