Wrapping Up
In this chapter, you harnessed the power of transformers on a variety of machine learning tasks. You learned about what transformers are and where the intuition behind transformers comes from. You learned about attention and how slight modifications to the original attention mechanism lead to the power of transformers. You used Bumblebee to make use of powerful pre-trained transformers to solve a variety of different tasks. You put Bumblebee in action on inference tasks, and you fine-tuned a pre-trained model with Bumblebee and Axon.
At this point, you’ve implemented the majority of the most important types of deep learning models in use. You know how to solve almost any type of problem on any type of data using Axon. Of course, almost ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access