# Request for Help needed

**URL:** <https://discuss.huggingface.co/t/request-for-help-needed/33471>\
**Category:** Models\
**Created:** [March 10, 2023, 3:59am UTC](https://discuss.huggingface.co/t/request-for-help-needed/33471 "2023-03-10T03:59:31Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Juheon](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/juheon/32/12152_2.png) [@Juheon](https://discuss.huggingface.co/u/Juheon)\
**Post date:** [March 10, 2023, 3:59am UTC](https://discuss.huggingface.co/t/request-for-help-needed/33471/1 "2023-03-10T03:59:31Z")

</div>

Hello, I am John who is currently contributing to Issue 17935 ([TF: XLA generation not working properly in some models · Issue #17935 · huggingface/transformers · GitHub](https://github.com/huggingface/transformers/issues/17935)) with @AdiaWu and @katiele47. We are trying to figure out the root of the software defects existing in the OPT model, but it is really hard to make a progress. Specifically, we are feeling difficulties what is preventing from generating XLA in OPT model.  
Attached screenshots show the simulations in a local environmnet. Would you mind giving me any suggestions?

 ![My project-1 (1)](https://us1.discourse-cdn.com/hellohellohello/original/2X/d/d0c14026446c309c09bd9fd9875d557053ac2234.png)