Interactive learning : load pretrained model


(anouar) #1

Hello ! i have a question about interactive learning , is there any chance to avoid ‘retrain’ the model from the beginning during interactive learning and just load a pretrained dialogue model that we previously trained on data stories . I think it’s complecated since the online_train function defined The agent from scratch and call the train function . Thank you


(Leo@Vocinity) #2

If you already have a trained model and want to skip that step just do this: python -m rasa_core.train
interactive --core models/dialogue
–nlu models/current/nlu
–endpoints endpoints.yml

As described over here: