Which model are you using? I tried the deepseek 34b or whatever, but it goes nuts at times. Also, what params do you have for Prompt Context Size and Max Completion Tokens?
4k/32k, if I remember right. An interesting thing to do is actually try to use a true coding model in a chat. I had one model puking out its stack overflow training data, down to including user IDs.
Oops.