https://huggingface.co/tencent/Hy-MT2-30B-A3B

#2423
by Yungchen-Jen - opened

I noticed you already did static/imatrix quants for Hy-MT2-1.8B and Hy-MT2-7B. It seems no one on Hugging Face has done quants for MT2-30B-A3B (https://huggingface.co/tencent/Hy-MT2-30B-A3B) yet. Even not from Tencent.

Thank you in advance!

Yungchen-Jen changed discussion title from [Static/Weighted Request] Hy-MT2-30B-A3B to https://huggingface.co/tencent/Hy-MT2-30B-A3B

well then we have to change it =)
It's queued!

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#Hy-MT2-30B-A3B-GGUF for quants to appear.

Nice, thanks again!

Well, the status page showed the following error message:

-2000 61 si Hy-MT2-30B-A3B error/1 ~HYV3ForCausalLM

Not meaning to hurry you guys up, but when you are available, can you take a look?

Maybe the latest version of llama.cpp has not supported it? If so, I can close the PR.

ERROR:hf-to-gguf:Model HYV3ForCausalLM is not supported

please try to get the PR, we will update llama cpp soon as well. Not sure if we have the latest, but I really dont think that we have it older than a week

Sign up or log in to comment