Skip to content

Releases: lucidrains/g-mlp-gpt

0.0.15

25 May 03:02
Compare
Choose a tag to compare
give tiny attention to Local SGU too, appropriately also sliding wind…

…ow local attention

0.0.14

25 May 01:05
Compare
Choose a tag to compare
prepare for local attention (to be paired with local SGU)

0.0.12

24 May 22:06
Compare
Choose a tag to compare
add causal tiny attention, for use with nonlocal SGU

0.0.11

23 May 17:17
Compare
Choose a tag to compare
allow for customizable gating activation in SGU, fix bug with padding

0.0.10

23 May 16:29
Compare
Choose a tag to compare
allow for customizable gating activation in SGU, fix bug with padding

0.0.9

21 May 05:05
Compare
Choose a tag to compare
assert

0.0.8

21 May 03:07
Compare
Choose a tag to compare
cache causal masks

0.0.7

21 May 02:44
Compare
Choose a tag to compare
easier hyperparams

0.0.6

21 May 02:32
Compare
Choose a tag to compare
use feedforwards for sibling block in reversible net, to save on memory

0.0.5

20 May 23:36
Compare
Choose a tag to compare
fix remaining bugs with axial folds