Skip to content

Latest commit

 

History

History
8 lines (3 loc) · 353 Bytes

README.md

File metadata and controls

8 lines (3 loc) · 353 Bytes

Demonstration of linear property of Transformers positional encodings

This notebook demonstrates the linear property of transformers from the paper Attention is all you need [https://arxiv.org/abs/1706.03762]. The code shows how positoinal encodings can be represented by linear transformaitons of each other inside the transformer architecture.