Hey Bartowski, just wanted to let you know that not working in LM Studio

#1
by rkh661 - opened

Seems like a cool one, maybe up there with QwQ, but no dice in LM Studio/Kobold etc. I tried your quants for this 32B and the 9B and neither is working? Not sure if its quants or llama.cpp issue? Thanks as always regardless.

Here is the error in LM Studio if it helps anyone:

🥲 Failed to load the model

Failed to load model

error loading model: error loading model architecture: unknown model architecture: 'glm4'

Should be out soon !!

It happened on my computer too.

Based on errors found by others, waiting on the PR to get merged with the fix:

https://github.com/ggml-org/llama.cpp/pull/12957

Thanks, Bartowski! You are the man! I saw you put a gate on the models, and that was very thoughtful.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment