Error while loading the custom Text classification model in python

I am facing an error while loading the custom text model which i have created.
The custom model is annotated using textcat.manual command.

I have followed the necessary steps to create the package of the custom model and have successfully installed it.

Now, while loading the model in python using Spacy commands , it is throwing the following error.

'FeedForward' object has no attribute 'W'

I have found a thread which talks about a similar issue.

How to deal with this issue?

This is possibly a dumb question, but: have you made sure that you’re loading the textcat model back with the same version as the one in your Prodigy installation? The model architecture isn’t necessarily compatible across versions.

If the spaCy versions match, could you paste the contents of the cfg file within the textcat model directory?