distillation that keeps useful behavior: what are you seeing?

[thetagrid15]

What worked for me was pretty simple. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.

My first guess would be this: If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.