# Adding categorical and numerical data to Bert model

**URL:** <https://discuss.huggingface.co/t/adding-categorical-and-numerical-data-to-bert-model/74004>\
**Category:** 🤗Transformers\
**Created:** [February 20, 2024, 3:20pm UTC](https://discuss.huggingface.co/t/adding-categorical-and-numerical-data-to-bert-model/74004 "2024-02-20T15:20:39Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![anon68600235](https://avatars.discourse-cdn.com/v4/letter/a/4af34b/32.png) [@anon68600235](https://discuss.huggingface.co/u/anon68600235)\
**Post date:** [February 20, 2024, 3:20pm UTC](https://discuss.huggingface.co/t/adding-categorical-and-numerical-data-to-bert-model/74004/1 "2024-02-20T15:20:39Z")

</div>

Hello everyone,  
I am trying to perform a multiclass text classification, and I am using, as stated in the title, TFBertForSequenceClassification, and more specifically the bert-base-multilingual-uncased (all my text data is lowercase).  
I learnt how to use the model after having followed the tutorials, however I think the model would benefit of additional numerical and categorical data, which I am discarding because I don’t know how to add it.  
I have already seen a post in which it is explained how to create a custom model, however the code uses pytorch that I don’t know yet ( I am learning tensorflow so I feel comfortable with it), so I a not able to get value out of it.  
Could someone help me on this topic?  
Thank you