Semanlink - Matteo Pagliardini sur X : "#DenseFormer, a simple modification that performs—after each transformer block—a weighted average of past representations."

Printer friendly

Search Tag:

Search Doc:

Preferences...

Matteo Pagliardini sur X : "#DenseFormer, a simple modification that performs—after each transformer block—a weighted average of past representations."

Tags:

About This Document

sl:bookmarkOf : https://twitter.com/MatPagliardini/status/1771168262174163406?s=20
sl:creationDate : 2024-03-23
sl:creationTime : 2024-03-23T11:44:52Z

File info

Bookmark of: https://twitter.com/MatPagliardini/status/1771168262174163406?s=20