Transformer models: Encoder-Decoders
A general high-level introduction to the Encoder-Decoder, or sequence-to-sequence models using the Transformer architecture. What is it, when should you use it?
This video is part of the Hugging Face course: http://huggingface.co/course
Related videos:
The Transformer architectutre: • The Transformer architecture
Encoder models: • Transformer models: Encoders
Decoder models: • Transformer models: Decoders
To understand what happens inside the Transformer network on a deeper level, we recommend the following blogposts by Jay Alammar:
The Illustrated Transformer: https://jalammar.github.io/illustrate...
The Illustrated GPT-2: https://jalammar.github.io/illustrate...
Understanding Attention: https://jalammar.github.io/visualizin...
Furthermore, for a code-oriented perspective, we recommend taking a look at the following post:
The Annotated Transformer, by Harvard NLP https://nlp.seas.harvard.edu/2018/04/...
Have a question? Checkout the forums: https://discuss.huggingface.co/c/cour...
Subscribe to our newsletter: https://huggingface.curated.co/