TRANSFORMERS & LLMs • 55 / 397
Follow text from characters to tokens, attention, transformers and generation.
Encoder-Decoder Model
An encoder-decoder model separately encodes input and decodes output.
Think of it like
Think of Encoder-Decoder Model as part of a very fast reader that repeatedly decides what information matters and what should come next.
Real life
Autocomplete, translation and chat assistants depend on concepts such as Encoder-Decoder Model.
SRE lens
Translation and sequence-to-sequence tasks often use this architecture.
Remember thisAn encoder-decoder model separately encodes input and decodes output.