Large Language Diffusion Model, GSAI-ML/LLaDA-8B-Instruct

#751
by SkyMind - opened

This is a language diffusion model, I don't believe there are any quants for that class of models at all.

https://huggingface.co/GSAI-ML/LLaDA-8B-Instruct
(MIT Licensed)

Thanks!

LLaDAModelLM is unfortunately not an architecture currently supported by llama.cpp so it is not possible to create GGUF quants of it until someone implements LLaDAModelLM support inside llama.cpp. Currently there doesn't exist any pull request implementing or an issue requesting LLaDAModelLM support. So it is unfortunately unlikely to happen anytime soon.

mradermacher changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment