InternVideo2-Stage1-1B-224p-K400 missing processor/config for Hugging Face transformers

Hello,

I am trying to use the Hugging Face model OpenGVLab/InternVideo2-Stage1-1B-224p-K400 with the transformers library for video feature extraction.

When I call:

from transformers import AutoImageProcessor
processor = AutoImageProcessor.from_pretrained("OpenGVLab/InternVideo2-Stage1-1B-224p-K400")

I get the error:

OSError: Can't load image processor for 'OpenGVLab/InternVideo2-Stage1-1B-224p-K400'.
... no preprocessor_config.json file

Looking at the repo, it only contains:

.gitattributes
1B_ft_k710_ft_k400_f16.pth
1B_ft_k710_ft_k400_f8.pth
README.md

There is no config.json or preprocessor_config.json.

This makes it incompatible with AutoImageProcessor / AutoVideoProcessor.

Request

Could you add the appropriate processor/config files (e.g. preprocessor_config.json, config.json) so the model can be loaded via transformers?

Or provide guidance on the recommended way to preprocess inputs for this model when using Hugging Face.

Thanks a lot for releasing this model!

Start by reproducing the AutoImageProcessor.from_pretrained call for OpenGVLab/InternVideo2-Stage1-1B-224p-K400 and inspect the model repository contents and README.md. Compare the existing .pth files with the processor and model metadata expected by transformers. Done means the model has the appropriate configuration files or clear preprocessing guidance for loading and extracting video features.