# Save CamemBert model wrapped in keras

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsave-camembert-model-wrapped-in-keras%2F1853%3E%5C
**Category:** Intermediate\
**Created:** [November 2, 2020, 9:38am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsave-camembert-model-wrapped-in-keras%2F1853 "2020-11-02T09:38:02Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Toropicana](https://avatars.discourse-cdn.com/v4/letter/t/2bfe46/32.png) [@Toropicana](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FToropicana)%5C
**Post date:** [November 2, 2020, 9:38am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsave-camembert-model-wrapped-in-keras%2F1853%2F1 "2020-11-02T09:38:02Z")

</div>

Hi,  
I am working on fine-tuning a camembert model for a text classification task.  
So here is what I am doing :  
I am loading a TFCamembertModel from pretrained base architecture.  
I call a function that builds the model as follow :

 ![image](https://us1.discourse-cdn.com/hellohellohello/original/2X/d/dff5ebb6d17479f0cc5fcd034337c4e8e284f325.png)

The layer in the model is basically the transformer outputting the CLS token used for classification.

My question is the following: how do I save the whole CamemBertModel i.g not just the layer which would force be to use the CLS token for downstream-task. I want the per word context vector, that I would average in a single vector representing whole text.

Tell me if that approach makes sense, of if I should rather use the CLS token.