Glossary term
Glossary term
Architecture
In general, any ML system that converts from a processed, dense, or internal representation to a more raw, sparse, or external representation.
Decoders are often a component of a larger model, where they are frequently paired with an encoder.
In sequence-to-sequence tasks, a decoder starts with the internal state generated by the encoder to predict the next sequence.
Refer to Transformer for the definition of a decoder within the Transformer architecture.
See Large language models in Machine Learning Crash Course for more information.
Created for this library
A translation vendor uses an encoder-decoder model where the decoder generates the target sentence one token at a time conditioned on the source.
A summarization vendor uses a decoder-only model to generate concise meeting summaries from full transcripts.
A code-generation vendor uses a decoder-only LLM to stream code suggestions token by token in the developer's IDE.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License