Could you convert also Qwen/Qwen2-0.5B-Instruct?

#1
by Felladrin - opened

Thanks for converting this model, @Minami-su !

The GGUF version of llamafied-Qwen allows for smaller splits than the original model when using gguf-split, which is great for running this model on mobile devices with wllama.

So, now that Qwen/Qwen2-0.5B-Instruct is out, could you kindly convert it too?

Thank you for your attention! The model has now been uploaded as Minami-su/Qwen2-0.5B-Instruct-llamafy.

Awesome! I've converted to GGUF and it's working great! (gguf-Qwen2-0.5B-Instruct-llamafy / gguf-sharded-Qwen2-0.5B-Instruct-llamafy)
Thanks again!

Felladrin changed discussion status to closed

Sign up or log in to comment