I think all frameworks support custom instruct templates, and know for a fact llama.cpp does due to my use of StudioLM, based on llama.cpp, in which I can alter the system / user / assistant templates.
Small specialized LLMs are going to be a thing the same way using frameworks is now.
I think all frameworks support custom instruct templates, and know for a fact llama.cpp does due to my use of StudioLM, based on llama.cpp, in which I can alter the system / user / assistant templates.