100% – I think a basic jinja implementation would be quite helpful. I do think a world where we have unified chat templates across transformers, llama.cpp, etc would be quite headache free 😀 There is an abandoned PR adding that in llama.cpp btw https://
github.com/ggerganov/llam
a.cpp/pull/9639
…

→ View original post on X — @reach_vb,