-
Notifications
You must be signed in to change notification settings - Fork 3
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
Unable to load saved model #7
Comments
Hi ,thank you for your issue, would it be easy to reproduce the error in a colab ? |
Sorry i dont understand, do you want me to try this on collab? This error currently was rendered on kaggle |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello, sorry im quite new to writing issues.
I trained a joint token classification and sequence classification model. To save it i used this:
trainer.save_model("multi_task/")
However trying to load the same model, i faced this issue
model_2 = tn.load_pipeline("/kaggle/working/multi_task","intent_classification", adapt_task_embedding=True)
I intend to load the model from this checkpoint for domain adaption
How do i address this issue? Also if you could redirect me to some resources to understand adapters that would be pretty helpful (i found out from the other issue posted here).
PS: Thank you for this incredible library- it saved me a lot of time
The text was updated successfully, but these errors were encountered: