update
199c240a
refactor transformer part 1
901d10eb
refactor part 2
ec05bbdf
refactor part 3
892b70de
make style
fd18f9ad
refactor part 4; modeling tests
4f1653c2
make style
412cd7cf
Merge branch 'main' into allegro-impl
bcba8589
refactor part 5
8f9ffa8f
refactor part 6
c76dc5a0
gradient checkpointing
015cc78b
pipeline tests (broken atm)
6b53b859
update
f64f2d05
add coauthor
2ef6a9e8
refactor part 7
e53dac24
add docs
f702af0c
Merge branch 'main' into allegro-impl
4f59d567
make style
3d412811
add coauthor
37e8a95f
a-r-r-o-w
marked this pull request as ready for review 1 year ago
make fix-copies
2c4645c0
undo unrelated change
e26604cd
revert changes to embeddings, normalization, transformer
bb321e7a
refactor part 8
174621f3
make style
2a820647
refactor part 9
762ccd5d
make style
cf5dec1d
Merge branch 'main' into allegro-impl
31544d46
DN6
approved these changes
on 2024-10-23
fix
d9eabf84
apply suggestions from review
cf010fc2
stevhliu
approved these changes
on 2024-10-23
Apply suggestions from code review
d44a5c8a
Merge branch 'main' into allegro-impl
ceb76789
update example
b036386b
Merge branch 'main' into allegro-impl
0fe8c510
yiyixuxu
approved these changes
on 2024-10-25
Merge branch 'main' into allegro-impl
2065adcd
remove attention mask for self-attention
9214f4a3
Merge branch 'main' into allegro-impl
723e5b51
update
3354ee18
copied from
28e57585
update
1ec17d51
update
4d6d4e43
a-r-r-o-w
merged
0d1d267b
into main 1 year ago
a-r-r-o-w
deleted the allegro-impl branch 1 year ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub