Jasper

Seconded, I'm getting the same error both when running locally and on a server.

@yasersakkaf did you make any progress on debugging this?

Should work already, I've gotten it working with: ```python from ctransformers import AutoModelForCausalLM # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no...

There are some models for long context tasks like storywriting that it'd be nice to use with a static RoPE scaling factor. +1 on this!

I did all that