Any timeline to release the code to train the LM + finetune on the other 11 tasks?

[Franck-Dernoncourt]

Thanks for the code release. Do you have any timeline to release the code to train the LM and finetune on the other 11 tasks?

[rodgzilla]

Hi @Franck-Dernoncourt, a few people are working on a PyTorch version of this code. We have recently added some classes that allow using this model for other tasks.

You can either use our version or translate it back to TensorFlow.

[madisonmay]

@Franck-Dernoncourt we're also working on a tensorflow wrapper that packages things up in a scikit-learn style interface.

For most tasks usage is as straightforward as:

model = Classifier()               # Load base model
model.fit(trainX, trainY)          # Finetune base model on custom data
predictions = model.predict(testX) # [{'class_1': 0.23, 'class_2': 0.54, ..}, ..]
model.save(path)                   # Serialize the model to disk