HF - Model Export Issue with OSS models

[ep150de]

🐛 Describe the bug

When trying to convert the OSS model from OpenAI using model export and model optimizer spaces from HuggingFace, I get the following error:

repro steps:
URL: https://huggingface.co/spaces/OpenVINO/nncf-quantization
https://huggingface.co/spaces/OpenVINO/export

Model source: https://huggingface.co/openai/gpt-oss-20b

Error: 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 This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

Environment

WebUI - Huggingface browser
Windows 11
Chrome Browser

Minimal Reproducible Example

repro steps:
URL: https://huggingface.co/spaces/OpenVINO/nncf-quantization
https://huggingface.co/spaces/OpenVINO/export

Model source: https://huggingface.co/openai/gpt-oss-20b

add model to hub model id input box (openai/gpt-oss-20b)

run
fails
see output error

Are you going to submit a PR?

• Yes I'd like to help by submitting a PR!

[ep150de]

suggested fix: (this must be done on the Huggingface space that runs the OpenVINO spaces on HF) or rebuild / clone space and run the commands to possibly fix.

You can update Transformers with the command pip install --upgrade transformers. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command pip install git+https://github.com/huggingface/transformers.git