[HN Gopher] Revealing example of self-attention, the building bl...
___________________________________________________________________
Revealing example of self-attention, the building block of
transformer AI models
Author : jostmey
Score : 8 points
Date : 2023-04-29 22:17 UTC (42 minutes ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| civilized wrote:
| What's this about? Run this code and you'll see something?
| legalizemoney wrote:
| I think so - OP if you were to include a Jupyter notebook it
| would save some time
| ybu wrote:
| In this context worth calling out Andrej Karpathy's youtube
| playlist on neural networks [0].
|
| In the last video ("Let's build GPT: from scratch...") Andrej
| codes up a transformer model, in conjunction with the paper [1].
|
| [0]
| https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThs...
|
| [1] https://arxiv.org/abs/1706.03762
___________________________________________________________________
(page generated 2023-04-29 23:00 UTC)