# Saving tokenizer's configuration

**URL:** <https://discuss.huggingface.co/t/saving-tokenizers-configuration/14955>\
**Category:** Beginners\
**Created:** [February 21, 2022, 3:39am UTC](https://discuss.huggingface.co/t/saving-tokenizers-configuration/14955 "2022-02-21T03:39:34Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Amalq](https://avatars.discourse-cdn.com/v4/letter/a/c68b51/32.png) [@Amalq](https://discuss.huggingface.co/u/Amalq)\
**Post date:** [February 21, 2022, 3:39am UTC](https://discuss.huggingface.co/t/saving-tokenizers-configuration/14955/1 "2022-02-21T03:39:34Z")

</div>

Hi,

I tried to fine-tuned language model using the following code

> <https://github.com/huggingface/notebooks/blob/master/examples/language_modeling.ipynb>

The issue I face is that the model is saved using (trainer.save\_mode()), but I don’t know how save tokenizer’s results as well?

I’ve tried to add tokenizer=tokenizer to trainer, but it ariesed error.  
any help is really appreciated.

---

<div class="post-metadata">

**Author:** ![tntchung](https://avatars.discourse-cdn.com/v4/letter/t/e19b73/32.png) [@tntchung](https://discuss.huggingface.co/u/tntchung)\
**Post date:** [February 24, 2022, 4:22pm UTC](https://discuss.huggingface.co/t/saving-tokenizers-configuration/14955/2 "2022-02-24T16:22:57Z")

</div>

hi,

As the tokenizer is AutoTokenizer, you can use tokenizer.save\_pretrained(your path) to save it.