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