search

Rishit-dagli / Nystromformer

An implementation of the Nyströmformer, using Nystrom method to approximate standard self attention
Apache License 2.0
55 stars 4 forks source link

Nystromformer Model #16

Closed Rishit-dagli closed 2 years ago

Rishit-dagli commented 2 years ago

Closes #5