# Storage-efficient ways to store models

**URL:** <https://discuss.huggingface.co/t/storage-efficient-ways-to-store-models/46112>\
**Category:** 🤗Transformers\
**Created:** [July 8, 2023, 6:01pm UTC](https://discuss.huggingface.co/t/storage-efficient-ways-to-store-models/46112 "2023-07-08T18:01:51Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![fatemystery](https://avatars.discourse-cdn.com/v4/letter/f/db5fbb/32.png) [@fatemystery](https://discuss.huggingface.co/u/fatemystery)\
**Post date:** [July 8, 2023, 6:01pm UTC](https://discuss.huggingface.co/t/storage-efficient-ways-to-store-models/46112/1 "2023-07-08T18:01:51Z")

</div>

I am fine-tuning several binary classification BERT models, all using bert-base-uncased. I understand that I can save my trained model and reload it later. I noticed that in the stored folder, the largest file is pytorch\_model.bin (478MB), which appeared in every model I saved. If this is the pre-trained model (before finetuning), can I save it only once and later using it when loading different models?