About how to finetune the InternVideo2-1B models on a customized dataset to get  an  InternVideo2-1B Clip model.

HI authors,

I appreciate your amazing work.

I am using  InternVideo2-1B as my work backbone. And want to train a clip model with our customized dataset.

Could you provide the scripts about how to fintune a clip model from  InternVideo2-1B checkpoint.

Or any instructions how to do that.

Thank you so much.