Google researchers publish the Transformer paper
The paper introduced an encoder–decoder architecture built entirely on attention, replacing recurrent computation with parallelizable self-attention.
TR1 English report
MODEL
Transformer
- Release date:
- 2017-06-12
- Parameters:
- 65M (base)/ 213M (big)
- Input/output:
- Text → Text
- Openness:
- Partially open-source
- Organization:
- Google DeepMind
Official links | Chat | Code Plan | Agent tools | API |
|---|---|---|---|---|
| Global |
Related English reports
English reports linked to this entity will appear here as their translations are published.
AI-assisted · reviewed