What do you mean by “make” what do you want it to do that you aren’t getting.

Maybe some existing model via ollama - llama-uncensored?

Do you need to add context with some specific set of data, should it be retrieval based or tuned or cross trained?

Does it even need to be an llm? What are you trying to actually achieve?

Which bits do you miss?

I do this too, maybe this explains why

On some cars that empty space where the clutch would be is the handbrake

What happens if you plug the stick into another box and check it for errors

To be fair, the title says more apps, not all apps…

🕷🕸

Self hosting what?

In general

1. Install docker
2. Copy and paste docker run commands from the getting started guide
3. Learn from mistakes