What are the Heads in Multihead Attention? (Multihead Attention Practically Explained)

The purpose of this video is to explore how multihead attention works in more detail and to understand how extending from single-head attention to the multihead case works in practice.
Code:
github.com/Bra...
Helpful Repos:
github.com/Cyb...
github.com/pyt...
Attention is All You Need:
arxiv.org/pdf/...
Music Credits:
Midnight Room by | e s c p | www.escp.space
escp-music.ban...
Synthetic by | e s c p | www.escp.space
escp-music.ban...
Please, Don’t Forget Me by | e s c p | www.escp.space
escp-music.ban...
Light Rain by | e s c p | www.escp.space
escp-music.ban...

[@mohamedkassar7441]

Wonderful thanks