Brett Kuprel
|
a4df279fd2
|
simplified attention and keys_values state resulted in decrease in inference time to 7.3 seconds (from ~10 seconds)
|
2022-06-29 13:56:29 -04:00 |
|
Brett Kuprel
|
80558b8a82
|
time the inference pass
|
2022-06-29 13:55:23 -04:00 |
|
Brett Kuprel
|
661ec976ac
|
simplified attention for torch model
|
2022-06-29 13:48:12 -04:00 |
|
Brett Kuprel
|
95afa18893
|
add gitattributes file
|
2022-06-29 12:45:41 -04:00 |
|
Brett Kuprel
|
764b5bbc0e
|
works with latest flax version 0.5.2, updated requirements.txt
|
2022-06-29 11:46:19 -04:00 |
|
Brett Kuprel
|
c4f613c89f
|
readme wording
|
2022-06-29 11:01:46 -04:00 |
|
Brett Kuprel
|
6046863805
|
readme wording
|
2022-06-29 11:00:38 -04:00 |
|
Brett Kuprel
|
2b552fe9db
|
readme wording
|
2022-06-29 10:54:01 -04:00 |
|
Brett Kuprel
|
b7c2414c76
|
readme wording
|
2022-06-29 10:47:08 -04:00 |
|
Brett Kuprel
|
4e62f85ab9
|
readme wording
|
2022-06-29 10:45:46 -04:00 |
|
Brett Kuprel
|
53695e32f7
|
updated readme with torch examples
|
2022-06-29 10:43:46 -04:00 |
|
kuprel
|
9d5bb34df0
|
default to torch+mega in colab
|
2022-06-29 10:37:12 -04:00 |
|
kuprel
|
d4af693133
|
updated colab to load model once and generate multiple times
|
2022-06-29 09:43:42 -04:00 |
|
Brett Kuprel
|
ed91ab4a30
|
refactored to load models once and run multiple times
|
2022-06-29 09:42:12 -04:00 |
|
kuprel
|
1ef9b0b929
|
added mega to colab
|
2022-06-29 06:44:07 -04:00 |
|
kuprel
|
ae0411dbcc
|
Cleanup
|
2022-06-29 06:25:52 -04:00 |
|
kuprel
|
0fe3e2d2b9
|
Merge pull request #28 from interfect/torch-logical-cores
Use all logical cores in Torch mode
|
2022-06-28 22:57:02 -04:00 |
|
Adam Novak
|
28c812c832
|
Use all logical cores in Torch mode
|
2022-06-28 22:26:51 -04:00 |
|
kuprel
|
97a55f169c
|
Updated colab to use torch+cuda
|
2022-06-28 22:12:36 -04:00 |
|
Brett Kuprel
|
1fbb209623
|
fixed bug with cuda in detokenizer
|
2022-06-28 22:02:35 -04:00 |
|
Brett Kuprel
|
764b0bc685
|
cuda in detokenizer from previous commit broke colab flax model, fixed
|
2022-06-28 21:36:48 -04:00 |
|
Brett Kuprel
|
d846cab1b6
|
Merge branch 'main' of https://github.com/kuprel/min-dalle
|
2022-06-28 21:28:50 -04:00 |
|
Brett Kuprel
|
17c96fe110
|
works with cuda
|
2022-06-28 21:28:36 -04:00 |
|
kuprel
|
0af6b1731f
|
Update setup.sh
removed `git lfs` dependency
|
2022-06-28 21:18:24 -04:00 |
|
kuprel
|
6f0be73579
|
Merge pull request #23 from andrewginns/main
Simplified requirements
|
2022-06-28 21:16:00 -04:00 |
|
kuprel
|
b8c4173181
|
Merge pull request #24 from TheFutureGadgetsLab/main
Fixed disabling of gradients in the torch code
|
2022-06-28 21:10:35 -04:00 |
|
Haydn Jones
|
a3a247e6ec
|
Fixed disabling of gradients in the torch code
|
2022-06-28 17:57:44 -06:00 |
|
Andrew Ginns
|
3c0c897977
|
Add flax model curl
|
2022-06-28 22:01:26 +01:00 |
|
Andrew Ginns
|
3af89066e8
|
Simplified requirements:
* No wandb login
* wandb install as part of requirements.txt
|
2022-06-28 21:34:57 +01:00 |
|
Brett Kuprel
|
9d6b6dcc92
|
previous commit broke flax model, fixed now
|
2022-06-28 12:54:58 -04:00 |
|
Evan Pratten
|
2bb4759f61
|
Explicitly call wandb as a python module.
This change allows wandb to be called on systems that do not automatically add python modules to $PATH
|
2022-06-28 12:51:24 -04:00 |
|
Brett Kuprel
|
5aa6fe49bf
|
use cuda if available
|
2022-06-28 12:47:11 -04:00 |
|
Brett Kuprel
|
8544f59576
|
use cuda if available
|
2022-06-28 12:38:31 -04:00 |
|
Brett Kuprel
|
aef24ea157
|
torch.no_grad(), cleanup
|
2022-06-28 12:16:44 -04:00 |
|
kuprel
|
1e2649148b
|
Merge pull request #19 from jedahan/patch-2
Support pip/pip3 binary names for setup
|
2022-06-28 11:35:20 -04:00 |
|
kuprel
|
57127ac616
|
Merge branch 'main' into patch-2
|
2022-06-28 11:34:46 -04:00 |
|
kuprel
|
6baeeec7f1
|
Merge pull request #17 from jedahan/patch-1
Exit script immediately if any command fails
|
2022-06-28 11:31:42 -04:00 |
|
Jonathan Dahan
|
fd0e808454
|
Support pip/pip3 binary names for setup
|
2022-06-28 11:20:23 -04:00 |
|
Jonathan Dahan
|
63a65372b0
|
Exit script immediately if any command fails
|
2022-06-28 11:13:10 -04:00 |
|
kuprel
|
7478c5ffa3
|
Simplified colab
|
2022-06-28 11:05:59 -04:00 |
|
kuprel
|
cbb8d4156f
|
Simplified colab
|
2022-06-28 11:01:31 -04:00 |
|
kuprel
|
407ea96865
|
Merge pull request #14 from rupa/main
fix requirements.txt
|
2022-06-28 09:25:58 -04:00 |
|
kuprel
|
6dbb5d7a7b
|
Login to weights and biases anonymously in colab
|
2022-06-28 09:19:52 -04:00 |
|
rupa
|
647eb950c2
|
fix requirements.txt
|
2022-06-28 09:18:23 -04:00 |
|
Brett Kuprel
|
34df2b97df
|
previous commit broke colab example, so adjusting flax requirement to 0.4.2 for now
|
2022-06-28 08:04:08 -04:00 |
|
Brett Kuprel
|
38ebe54a38
|
works with latest flax version 0.5.2 now
|
2022-06-28 07:12:29 -04:00 |
|
kuprel
|
50e1e74c4a
|
Merge pull request #6 from osanseviero/patch-1
Update README.md
|
2022-06-28 06:28:21 -04:00 |
|
kuprel
|
332677b032
|
Fixed bug in colab notebook setup process
|
2022-06-28 06:09:52 -04:00 |
|
Omar Sanseviero
|
efa40ab321
|
Update README.md
|
2022-06-28 09:25:56 +02:00 |
|
Brett Kuprel
|
6260252348
|
update readme
|
2022-06-27 22:08:29 -04:00 |
|