Code for Scaling Transformer to 1M tokens and beyond with RMT (arxiv.org) (github.com) 1 points by mysterybox 3y ago ↗ HN
[–] mysterybox 3y ago ↗ I found this interesting link in paper, so this can be used as ready code for RMT Transformerhttps://github.com/booydar/t5-experiments/tree/scaling-repor...
4 comments
[ 2.9 ms ] story [ 15.6 ms ] threadhttps://github.com/booydar/t5-experiments/tree/scaling-repor...
https://github.com/booydar/t5-experiments/blob/scaling-repor...