English
← Back to AI Technology

Model architecture

Transformer

An attention-based neural architecture that processes sequence positions in parallel. It became a foundation for many modern language and multimodal models.

Reference period
2017
Last reviewed

Key terms

  • self-attention
  • encoder
  • decoder
  • positional encoding

Connected across the project

Primary sources

  1. Attention Is All You Need

This is a curated technical map, not a claim of comprehensive coverage.