the beginning and add deprecated flag to models.json so older versions will
show a model, but later versions don't. This will allow us to transition
away from models < ggmlv2 and still allow older installs of gpt4all to work.
Major change to the backend that allows for pluggable versions of llama.cpp/ggml. This was squashed merged from dlopen_backend_5 where the history is preserved.
