# Using bert tokenizer in Electra model

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-bert-tokenizer-in-electra-model%2F10330%3E%5C
**Category:** 🤗Transformers\
**Created:** [September 27, 2021, 6:58am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-bert-tokenizer-in-electra-model%2F10330 "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](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJeydev)%5C
**Post date:** [September 27, 2021, 6:58am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-bert-tokenizer-in-electra-model%2F10330%2F1 "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?