Model size too large?

Using Streamlit
1

Hi everyone,
I am deploying my first streamlit app on the Community cloud and am constantly encountering errors. My first obstacle was that the requirements were not read in, but I could solve that problem. The app now loads all required libraries, which is great. However, I have another problem which I am stuck at for a month now.
When I want to run my app the following error pops us directly after deployment.

image
image1330×296 20.9 KB

After a few experiments I assume that it could be because of the size of the used machine learning model, which is a tiny bit larger than 1GB. What is irritating me is that the error message indicates that it runs locally. At least that’s what I attribute the “system memory” part in the error message to.

Help would be much appreciated as I already tried a lot to troubleshoot the app.

  1. Are you running your app locally or is it deployed?
    Deployed

  2. If your app is deployed:
    a. Is it deployed on Community Cloud or another hosting platform? → Community Cloud

    b. Share the link to the public deployed app. → https://lid-app.streamlit.app/

  3. Share the link to your app’s public GitHub repository → GitHub - Wolftess/LID: A language identification systems working for over 400 languages, including several German dialects like Tyrolean, Swabian and Low Saxon.

  4. Share the full text of the error message (not a screenshot). → see above

  5. Share the Streamlit and Python versions. → latest version streamlit, python_version = “3.10.12”

Thanks a lot!

2

You might have exceeded the resource limits.

Have a look on this guide on resource limits.

Post your error message as text not as image.

3

This topic was automatically closed 180 days after the last reply. New replies are no longer allowed.