Transfer NLP Documentation

Transfer NLP is a framework built on top of PyTorch which goal is to achieve 2 kinds of Transfer:

  • easy transfer of code: the framework should be modular enough so that you don’t have to re-write everything each time you experiment with a new architecture / a new kind of task

  • easy transfer learning: the framework should be able to easily interact with pre-trained models and manipulate them in order to fine-tune some of their parts.

You can try the library on this Colab Notebook., which shows how to use the framework on several examples. All examples on these notebooks embed in-cell Tensorboard training monitoring!