Commit History

feat: layernorm > rmsnorm in long runs
0f2cf98

boris commited on

fix: use correctly cache during inference + allow unscan (#170)
42968cf
unverified

boris commited on

fix: allow non-scanned models (#168)
8ae9176
unverified

boris commited on

feat(demo): do not log search
3500e67

boris commited on

feat: vmap optimizer (#166)
b993d27
unverified

boris commited on

feat(demo): use fixed commit
2f1e5d9

boris commited on

doc: reference dalle playground
648305a

boris commited on

feat: scan layers + gradient checkpointing (#161)
07a6f9a
unverified

boris commited on

Merge pull request #162 from borisdayma/demo-improvements
0199604
unverified

Pedro Cuenca commited on

Merge branch 'main' of https://github.com/borisdayma/dalle-mini into main
bcd360f

boris commited on

Style: run isort.
58b9afd

Pedro Cuenca commited on

Style: run black.
2d6dbdd

Pedro Cuenca commited on

Display info about model and run, below predictions.
13caa60

Pedro Cuenca commited on

Update year: 2021-2022
f58c732

Pedro Cuenca commited on

Log dates
687a914

Pedro Cuenca commited on

Move client api to backend.py
63679e9

Pedro Cuenca commited on

feat: better multi-node support (#158)
728a3c3
unverified

boris commited on

doc: link to new demo
49be45e

boris commited on

feat(demo): high load
d68264e

boris commited on

feat(demo): update space
20a3626

boris commited on

feat(text): support emojis (#154)
7ef7bd9
unverified

boris commited on

feat: update shampoo
9ecdd3f

boris commited on

fix: smelu
7f2f8ed

boris commited on

fix: sinkformer
2c583b3

boris commited on

fix: support smelu
a2dcee4

boris commited on

fix: einops is required
179282e

boris commited on

feat: allow relative position (#156)
769d20a
unverified

boris commited on

feat: sinkhorn in lse mode (#155)
00d4661
unverified

boris commited on

feat(demo): update model
b9a1a7d

boris commited on

fix: sinkformer gradient
eed4896

boris commited on

feat(model): allow bias (#152)
361a994
unverified

boris commited on

feat(train): google-cloud-storage is optional
02b2308

boris commited on

feat(train): rename logged config
955dc20

boris commited on

feat: add sinkformer + custom final ln + pre-ln (#151)
f139b0b
unverified

boris commited on

feat: placeholders for more config
69bcbeb

boris commited on

feat: add mini_glu config
a7e5050

boris commited on

feat: force final ln in encoder
32f4ba5

boris commited on

feat: allow more configurations
5bd4c20

boris commited on

fix: DeepNet doesn't scale weights of embedding/output layers (#150)
503d6b4
unverified

Shuming Ma Shuming Ma commited on

feat: remove unecessary LN
02824a7

boris commited on

feat: update mini config
d9a16f2

boris commited on

feat: add cogview
472c4cc

boris commited on

fix(textnormalizer): consider utf8 on windows (#148)
3b8d8cb
unverified

illtellyoulater commited on

feat: implement transformer variants (#144)
542378c
unverified

boris commited on

feat(train): log norm and histograms (#143)
b7b619a
unverified

boris commited on

feat(data): super conditioning (#141)
7939874
unverified

boris commited on

feat: support pod (#139)
803ccbf
unverified

boris commited on

fix: no gradient checkpointing for new model
2e02683

boris commited on

feat: no gradient checkpointing for params init
b798ed3

boris commited on

feat: update configs
79557f9

boris commited on