# Converting TF checkpoint with missing .meta file

**URL:** <https://discuss.huggingface.co/t/converting-tf-checkpoint-with-missing-meta-file/14402>\
**Category:** Models\
**Created:** [February 4, 2022, 4:59am UTC](https://discuss.huggingface.co/t/converting-tf-checkpoint-with-missing-meta-file/14402 "2022-02-04T04:59:01Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![sauravpr](https://avatars.discourse-cdn.com/v4/letter/s/97f17d/32.png) [@sauravpr](https://discuss.huggingface.co/u/sauravpr)\
**Post date:** [February 4, 2022, 4:59am UTC](https://discuss.huggingface.co/t/converting-tf-checkpoint-with-missing-meta-file/14402/1 "2022-02-04T04:59:01Z")

</div>

A .meta file is missing in each of the 24 smaller Bert models provided by google-research

> **[GitHub - google-research/bert: TensorFlow code and pre-trained models for BERT](https://github.com/google-research/bert#pre-trained-models)**
>
> TensorFlow code and pre-trained models for BERT. Contribute to google-research/bert development by creating an account on GitHub.

Would the TF to pytorch conversion file – convert\_bert\_original\_tf\_checkpoint\_to\_pytorch.py from Hugging Face – still be applicable

> <https://github.com/huggingface/transformers/blob/main/src/transformers/models/bert/convert_bert_original_tf_checkpoint_to_pytorch.py>

I am very new to TF, so please forgive me if this is a silly question.