gguf / mlx format?

[Alexander Potemkin]

Hello and thanks for open-sourcing the model!

As it doesn't seem to be any ready to use gguf or mlx formats (for llama.cpp and macos respectively) - is there any chance you can give a hint on how to convert YaLM there?

It would be of real help to enable model to run on non-Nvidia enabled HW, like any modern pc and mobile.

Thanks in advance!