AI engineering glossary · Transformers LLM architecture
What is sequence-to-sequence model?
Sequence-to-sequence model (also called Seq2seq): A model that reads one sequence and produces another sequence whose length may differ. Early versions used a recurrent encoder and decoder; modern ones use Transformers. Typical uses are translation, summarisation and speech recognition.
Sequence-to-sequence model: an example
A seq2seq model converts a 12-word English sentence into a 10-word Tamil sentence.
Related terms
More Transformers LLM architecture terms
- Shared expert
- Sinusoidal positional encoding
- Sliding window attention
- Sparse attention
- Sparse autoencoder
- State space model
- Switch Transformer
- T5
Where you learn it
Sequence-to-sequence model is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.