The Transformer architecture is made up of two core components: an encoder and a decoder. The encoder contains layers that process input data, like text and images, iteratively layer by layer.

Learn With Jay. Transformers’ Encoder Architecture Explained — No Phd Needed! Posted: May 7, 2025 | Last updated: May 7, 2025. Finally understand how encoder blocks work in transformers, with ...

But not all transformer applications require both the encoder and decoder module. For example, the GPT family of large language models uses stacks of decoder modules to generate text.

Transformers are a hot topic these days because they are the architecture of LLMs like ChatGPT and Bard. They use an encoder-decoder structure and allow for an attention mechanism .