Mega Pytorch Versions Save

Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena

0.1.0

8 months ago

0.0.15

1 year ago

0.0.14

1 year ago

0.0.12

1 year ago

0.0.11

1 year ago

0.0.10

1 year ago

0.0.9

1 year ago

0.0.8

1 year ago

0.0.6

1 year ago