# BartForConditionalGeneration : lm\_head layer dimension change

**URL:** <https://discuss.huggingface.co/t/bartforconditionalgeneration-lm-head-layer-dimension-change/15421>\
**Category:** 🤗Transformers\
**Created:** [March 7, 2022, 3:13am UTC](https://discuss.huggingface.co/t/bartforconditionalgeneration-lm-head-layer-dimension-change/15421 "2022-03-07T03:13:40Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![anon49134782](https://avatars.discourse-cdn.com/v4/letter/a/47e85d/32.png) [@anon49134782](https://discuss.huggingface.co/u/anon49134782)\
**Post date:** [March 7, 2022, 3:13am UTC](https://discuss.huggingface.co/t/bartforconditionalgeneration-lm-head-layer-dimension-change/15421/1 "2022-03-07T03:13:40Z")

</div>

Hi,

I’m trying to create a simple seq2seq generation model based on BartForconditionalGeneration.

The original input dimension of lm\_head layer is 1024.

But I have changed it to 1244 for some purpose.

like this

```auto
model.lm_head 
Linear(in_features=1224, out_features=50266, bias=False)

```

But when I implement forward() method, I run into this error.

 ![image](https://us1.discourse-cdn.com/hellohellohello/original/2X/c/c9d44617e86e30173844c29c86d8821acbc3ea3a.png)

As you can see, the input dimension is still 1024.

How can I solve this error?