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: [ Ссылка ]

Related videos:
- The Transformer architectutre: [ Ссылка ]
- Encoder models: [ Ссылка ]
- Decoder models: [ Ссылка ]

To understand what happens inside the Transformer network on a deeper level, we recommend the following blogposts by Jay Alammar:
- The Illustrated Transformer: [ Ссылка ]
- The Illustrated GPT-2: [ Ссылка ]
- Understanding Attention: [ Ссылка ]

Furthermore, for a code-oriented perspective, we recommend taking a look at the following post:
- The Annotated Transformer, by Harvard NLP [ Ссылка ]

Have a question? Checkout the forums: [ Ссылка ]
Subscribe to our newsletter: [ Ссылка ]

свернуть