Skip to content

Latest commit

 

History

History
13 lines (8 loc) · 414 Bytes

README.md

File metadata and controls

13 lines (8 loc) · 414 Bytes

bert_attention_map

This repository contains the data and code for the following paper:

APA style reference.

Please cite the paper if you use the resources in the repository.

(The code is adapted from Vig, J. (2019). A multiscale visualization of attention in the transformer model. arXiv preprint arXiv:1906.05714.)

Compatibility

torch 1.31.1
transformsers 4.27.2