Not working with sample code
Getting errorValueError: The checkpoint you are trying to load has model type
qwen2_moe but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date
Did you figure out how to fix this I can't get it to run in collab at all from this error.
To make this work in google colab you can use a gpu runtime then run these commands in a block then run example code.
!git clone https://github.com/huggingface/transformers.git
%cd transformers
!pip install optimum
!pip install auto-gptq
!pip install -e .
Then restart runtime to use packages installed then use the example code. Hopefully this helps anyone trying to use this model in colab as just installing transformers from source didn't matter as these dependencies had to be installed in this order for it to work on my instance.
Did you figure out how to fix this I can't get it to run in collab at all from this error.
I was checking it locally, I installed transformers from the source(git) and it worked!