System Info
I have a donut model with some slight customizations to the mbart decoder (added gqa and moe). It works fine on 4.36.2 and 4.37.2 for training.
But inference only works on 4.36.2. When I run inference on 4.37.2, then the output degenerates into repetition. @amyeroberts
Here is an example (the text has been ocred with donut, then rendered back onto a page image):
This is with 4.36.2:
And this is with 4.37.2:
Everything else is identical (same system, same packages). I don't see anything obvious in the release notes that would cause this.
Who can help?
No response
Information
Tasks
Reproduction
You should see different output with different transformers versions.
Expected behavior
I expect the output to be the same with both versions, and to not degenerate into repetition.
System Info
I have a donut model with some slight customizations to the mbart decoder (added gqa and moe). It works fine on 4.36.2 and 4.37.2 for training.
But inference only works on 4.36.2. When I run inference on 4.37.2, then the output degenerates into repetition. @amyeroberts
Here is an example (the text has been ocred with donut, then rendered back onto a page image):
This is with 4.36.2:
And this is with 4.37.2:
Everything else is identical (same system, same packages). I don't see anything obvious in the release notes that would cause this.
Who can help?
No response
Information
Tasks
examplesfolder (such as GLUE/SQuAD, ...)Reproduction
python benchmark/recognition.py --max 1 --debugYou should see different output with different transformers versions.
Expected behavior
I expect the output to be the same with both versions, and to not degenerate into repetition.