# Different results between pipeline and model() with multiple inputs

**URL:** <https://discuss.huggingface.co/t/different-results-between-pipeline-and-model-with-multiple-inputs/17014>\
**Category:** 🤗Transformers\
**Created:** [April 20, 2022, 5:29pm UTC](https://discuss.huggingface.co/t/different-results-between-pipeline-and-model-with-multiple-inputs/17014 "2022-04-20T17:29:18Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Ilias](https://avatars.discourse-cdn.com/v4/letter/i/3bc359/32.png) [@Ilias](https://discuss.huggingface.co/u/Ilias)\
**Post date:** [April 20, 2022, 5:29pm UTC](https://discuss.huggingface.co/t/different-results-between-pipeline-and-model-with-multiple-inputs/17014/1 "2022-04-20T17:29:18Z")

</div>

![Screen Shot 2022-04-20 at 1.18.19 PM](https://us1.discourse-cdn.com/hellohellohello/original/2X/2/2b4acfc3b889dff0ec535774c6e698274c8d8c2c.png)

Weirdly enough, I am not able to reproduce the results from `torch.softmax(model(**tokenizer([['Thanks ', ' You']], return_tensors="pt",padding=True,truncation=True)).logits, dim=1).detach().numpy()` using the pipeline…

It seems like the issue come with the way I have set up the tokenizer but I can’t seem to find what I am doing wrong. Would you happen to know what it could be?