-
Notifications
You must be signed in to change notification settings - Fork 724
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Loading a fine tuned Seq2Seq MarianMT model gives wrong predictions #1571
Comments
Do you get any warnings when you reload the model? (Set up logging if you haven't: Does it work as expected if you reload the model with Simple Transformers and use |
I did get the warning saying that not all weights are initialized when loading the model using |
To load with ST, you'd do:
In theory, |
i initialized and trained the following model:
After training,
model.predict(['this is a test'])
gives me desired output.However, when I loaded back this model to make prediction. The output is off:
Anything i missed?
The text was updated successfully, but these errors were encountered: