# Example script for VideoMAEForPreTraining

**URL:** <https://discuss.huggingface.co/t/example-script-for-videomaeforpretraining/57164>\
**Category:** 🤗Transformers\
**Created:** [October 3, 2023, 12:04am UTC](https://discuss.huggingface.co/t/example-script-for-videomaeforpretraining/57164 "2023-10-03T00:04:11Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![abhaydoke](https://avatars.discourse-cdn.com/v4/letter/a/848f3c/32.png) [@abhaydoke](https://discuss.huggingface.co/u/abhaydoke)\
**Post date:** [October 3, 2023, 12:04am UTC](https://discuss.huggingface.co/t/example-script-for-videomaeforpretraining/57164/1 "2023-10-03T00:04:11Z")

</div>

Hello everyone,

I am looking for an example script which uses [VideoMAEForPreTraining](https://huggingface.co/docs/transformers/main/en/model_doc/videomae#transformers.VideoMAEForPreTraining) for pretraining on a video dataset. [This](https://github.com/huggingface/notebooks/blob/main/examples/video_classification.ipynb) colab shows how to use VideoMAEForVideoClassification for finetuning task, but I am looking for more pointers on how to use VideoMAEForPreTraining.

I appreciate any help. Thanks.