Very cool and works pretty well!

I seem to only get gibberish out of it. I built their forked version of llama.cpp and this is what I'm getting using their recommended commandline:

> Explain quantum computing in simple terms.

\( ,

None ( no for the. (,./. all.2... the ..... by/

I'm fascinated by these smaller models.

The amount of progress they've been making is incredible.

Is anyone following this space more closely? Is anyone predicting performance at certain parameter sizes will plateau soon?

Unlike the frontier models, these don't seem to be showing much progress of slowing down.