Nils Herzig

Think about exposing the max iterations setting to the webui. Users might be able to abuse this. Maybe just accept a range.

 could you plase give me some examples?

> This is qwen 1.5 32b Damn 32b sounds nice, especially with GQA. I really need some more vram.  Curling the backend works, i guess its some sort of...

Looks like the backend isn't able to connect to ollama. Can you show me your ollama start command, maybe it's not listening on the right interface? Btw fantastic bug report...

No problem :). I know the setup process isn't there yet. Im working on a couple of tutorials especially for the whole ollama and networking part :)