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: huggingface.co/...
Related videos:
The Transformer architectutre: • The Transformer archit...
Encoder models: • Transformer models: En...
Decoder models: • Transformer models: De...
To understand what happens inside the Transformer network on a deeper level, we recommend the following blogposts by Jay Alammar:
The Illustrated Transformer: jalammar.githu...
The Illustrated GPT-2: jalammar.githu...
Understanding Attention: jalammar.githu...
Furthermore, for a code-oriented perspective, we recommend taking a look at the following post:
The Annotated Transformer, by Harvard NLP nlp.seas.harva...
Have a question? Checkout the forums: discuss.huggin...
Subscribe to our newsletter: huggingface.cu...