You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When I train setfit for multiclass classification using huggingface trainer which I am using save_step arguments, I can not use the model.predict() method for getting predictions. I am getting the below not fitted error.
model.predict() only work when i am loading the model with save_pretrained() method, but i still can not use other saved steps models for prediction, there is only one useable model which saved with save_pretrained_method().
I did not face with the issue when train binary classification model using same setup.
The text was updated successfully, but these errors were encountered:
When I train setfit for multiclass classification using huggingface trainer which I am using save_step arguments, I can not use the model.predict() method for getting predictions. I am getting the below not fitted error.
model.predict() only work when i am loading the model with save_pretrained() method, but i still can not use other saved steps models for prediction, there is only one useable model which saved with save_pretrained_method().
I did not face with the issue when train binary classification model using same setup.
The text was updated successfully, but these errors were encountered: