Cool I didn’t know llamacpp could do gpu acceleration at all. I’m going to look into that.

I think I might be on to something that contributes to the problem. The built-in “KoboldGPT chat” option puts some example queries in its context memory. They aren’t very long responses so I think it’s just seeing that and using it as a guideline for what to say which results in shorter answers.

If I use the “new chat” option instead of “KoboldGPT chat”, it makes it so that nothing is in the context. No prompt and no memory. This way when I tell it to write 500 words of crap, it doesn’t quite write that much but it’s a lot better than before. Pressing enter to make it generate more text works more often this way too.

Coqui xtts is broken right now, at least on Debian. I did not try xtts2. Yet turns out I already tried that one. After my computer is done being frozen from my latest hacking attempt to make a borked tts python maybe work, I’ll add whatever the error is.

The docker installation for the first one is broken just FYI but I guess I should be trying to use whichever one is the most up to date for higher chances of success.

I kind of don’t really care anymore. Fuck all this broken shit. I’m sure whichever leading github repository that does this same thing a couple years from now will be easier to install so I’ll just wait until then to mess with it.

His coke high wore off around 45 minutes in