mistral-community

/

Mixtral-8x22B-v0.1-AWQ

like 29

Assuming this is a GEMM 128 group size AWQ quant, here is the missing quant_config.json.

I do alot of AWQ quants, and the community will remind me when I forget to add one to my repo ;)

cc @MaziyarPanahi

Hi @Suparious

I used the AutoAWQ that HuggingFace offers and automatically uploads the model to the hub. I don't see this file. Can you point me to one and I can create it and upload it now.

Thanks @mrfakename

It is in this pull request, ready to merge

Oh my!!! It's one of those days when I don't know the difference between an issue and the pull request! 😂