TRANSFORMERS & LLMs • 53 / 397
Follow text from characters to tokens, attention, transformers and generation.

Encoder-Only Model

An encoder-only model mainly produces representations of input rather than freely generating long continuations.

Think of it like

Think of Encoder-Only 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-Only Model.

SRE lens

It can be suited to classification or embeddings.

Remember thisAn encoder-only model mainly produces representations of input rather than freely generating long continuations.
AIForSREJump to a concept
Search is optional. The main journey is simply ↓ Next.