gpt_oss error when running on kaggle

#72
by thehai - opened

I face the error when initalizing the model : ValueError: The checkpoint you are trying to load has model type gpt_oss 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 This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

Anyone can help me to fix this?

you need to install the latest transformers. Btw transformers main, it should even work on a T4 ! Please try to following google colab: https://colab.research.google.com/drive/15DJv6QWgc49MuC7dlNS9ifveXBDjCWO5?usp=sharing

Yes! you can find more details here: https://cookbook.openai.com/articles/gpt-oss/run-colab

Sign up or log in to comment