# Using bert tokenizer in Electra model

**URL:** <https://discuss.huggingface.co/t/using-bert-tokenizer-in-electra-model/10330>\
**Category:** 🤗Transformers\
**Created:** [September 27, 2021, 6:58am UTC](https://discuss.huggingface.co/t/using-bert-tokenizer-in-electra-model/10330 "2021-09-27T06:58:21Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Jeydev](https://avatars.discourse-cdn.com/v4/letter/j/dc4da7/32.png) [@Jeydev](https://discuss.huggingface.co/u/Jeydev)\
**Post date:** [September 27, 2021, 6:58am UTC](https://discuss.huggingface.co/t/using-bert-tokenizer-in-electra-model/10330/1 "2021-09-27T06:58:21Z")

</div>

I wonder if an untrained Electra model loaded from config with same number of classes(Tokens) as bert tokenizer, will it be able to use bert tokenizer and do the training part?