# How to use fine-tuned model

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-use-fine-tuned-model%2F5799%3E%5C
**Category:** Beginners\
**Created:** [April 27, 2021, 8:48am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-use-fine-tuned-model%2F5799 "2021-04-27T08:48:04Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![yucheng](https://avatars.discourse-cdn.com/v4/letter/y/eada6e/32.png) [@yucheng](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fyucheng)%5C
**Post date:** [April 27, 2021, 8:48am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-use-fine-tuned-model%2F5799%2F1 "2021-04-27T08:48:04Z")

</div>

hi,  
I use trainer.train() to fine-tune my custome NER dataset with bert model,  
and train.save\_model() to save the models that having different hyperparameters.

how should I do to reload my different model?

---

<div class="post-metadata">

**Author:** ![sgugger](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/sgugger/32/2291_2.png) [@sgugger](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsgugger)%5C
**Post date:** [April 27, 2021, 11:52am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-use-fine-tuned-model%2F5799%2F2 "2021-04-27T11:52:21Z")

</div>

You can just do

```auto
from transformers import AutoModel

model = AutoModel.from_pretrained(ouput_dir_of_your_trainer)

```