sennnnn
|
2b17f4fac2
|
Merge main branch.
Former-commit-id: 800ca74fad0d9021f1e96ddf32cd93cdb37cbbe0
|
2024-03-11 14:35:17 +08:00 |
|
lb203
|
14e217a698
|
Update README.md
Former-commit-id: 1f94f2721f35670aeae8dbfb7c0a5abd06cd2aee
|
2024-03-10 21:37:01 +08:00 |
|
lb203
|
d4aa360c50
|
Update README.md
Former-commit-id: 2808edf11005e04aa730971a786d1a4e3bca88b5
|
2024-03-10 21:16:15 +08:00 |
|
lb203
|
93b624e62d
|
Update README.md
Former-commit-id: 64d147863368aeef479ad25f2e5463fdcb76de46
|
2024-03-10 20:27:46 +08:00 |
|
lb203
|
f423fc7538
|
Update README.md
Former-commit-id: 6d41cfe906f97dbed1cea8c9ed06a1f6dc84308e
|
2024-03-10 20:25:48 +08:00 |
|
LinB203
|
a7165b506e
|
clean script
Former-commit-id: 02c61f63a8539a31516b92f5bb7c2d2e428ca7d7
|
2024-03-10 18:34:37 +08:00 |
|
lb203
|
740363460f
|
Update README.md
Former-commit-id: 7a62dec060c91b02ca556451266e6f3ef28e03e7
|
2024-03-10 18:27:50 +08:00 |
|
lb203
|
aeb3081341
|
Update pyproject.toml
Former-commit-id: 5c379b6e4515ad75b89cdebbc5cd490c9a821d78
|
2024-03-10 18:21:50 +08:00 |
|
lb203
|
fb62b8ff7e
|
Update README.md
Former-commit-id: 059d9e863958cfd679dbb8d365de6cd933e284fc
|
2024-03-10 18:20:28 +08:00 |
|
lb203
|
74494966bd
|
Update README.md
Former-commit-id: 87636c1dc2275c4da77c6368a0f4425bea15dc12
|
2024-03-10 18:15:21 +08:00 |
|
LinB203
|
b57709108a
|
train 1080p video
Former-commit-id: 74625142ef892f9e7fa459b2f98f2f7ae5b36d6a
|
2024-03-10 18:08:23 +08:00 |
|
lb203
|
1f4d4cbdfd
|
Merge pull request #112 from sennnnn/diffusion_deepspeed_fix
🐛 [BUG] Add base config for Latte
Former-commit-id: 825aa78ded6a5436d53d488b2c2250ac41b2bff9
|
2024-03-10 15:29:50 +08:00 |
|
sennnnn
|
995454b518
|
Add base config.
Former-commit-id: d37c551a0421d6b73dee26060b517c46d8217e4f
|
2024-03-10 15:24:40 +08:00 |
|
lb203
|
3d3ea0c818
|
Update README.md
Former-commit-id: 582070d4f97c4a4398dcb9a6699f4ab6e980c812
|
2024-03-10 15:17:18 +08:00 |
|
LinB203
|
6dae0b1c0c
|
deepspeed
Former-commit-id: 6179a4b0e7d06caed4201a27679abc64615febe6
|
2024-03-10 15:08:12 +08:00 |
|
lb203
|
557b062028
|
Merge pull request #110 from sennnnn/diffusion_deepspeed
⭐[Feature] Support deepspeed for latte training.
Former-commit-id: 59e731cb98915a2635547cad904ced7d9fcf73f4
|
2024-03-10 14:48:03 +08:00 |
|
sennnnn
|
28b7fc4bae
|
Fix typos.
Former-commit-id: c10330d373466f3c1ab455bfb391569b9175bc3a
|
2024-03-10 13:17:44 +08:00 |
|
sennnnn
|
61f9c5bced
|
Add some comments.
Former-commit-id: d5b5bd7743edde6a63dc74457bded0f8c56be1c2
|
2024-03-10 12:23:42 +08:00 |
|
sennnnn
|
f3274235d8
|
Support deepspeed zero2 and zero2_offload for latte training.
Former-commit-id: c87e95dd357e6fa6d6fb2dcfee781bc49c039e13
|
2024-03-10 11:27:33 +08:00 |
|
sennnnn
|
81c455e878
|
Refactor latte.
Former-commit-id: 7408fd0ee16247afc3d4ba43b8c8e7dfb1091a97
|
2024-03-10 11:25:56 +08:00 |
|
sennnnn
|
443bab1364
|
Refactor latte.
Former-commit-id: 304534269f105578097bc16ab497636ad59fd9b2
|
2024-03-10 11:25:50 +08:00 |
|
sennnnn
|
bfe4f15694
|
Fix mixed_precision bugs of latte.
Former-commit-id: d70a551972e04d95444d46cdbe2bfb16ad099fcb
|
2024-03-10 11:25:07 +08:00 |
|
sennnnn
|
ee3810a585
|
Decouple mixed_precision and gradient_accumulation to command args.
Former-commit-id: 903d473d1432eb492a87efe184d03439f643b92d
|
2024-03-10 11:24:39 +08:00 |
|
lb203
|
d6d54da131
|
typo
Former-commit-id: 9e87366e906ed19726c8905afb27b5df4d4e1512
|
2024-03-10 11:15:14 +08:00 |
|
LinB203
|
f034826c6d
|
fixed attn_mask in flash-attn
Former-commit-id: 5e2504f429a342b75bc7a9004cee7b3f75582ee3
|
2024-03-10 11:12:12 +08:00 |
|
lb203
|
74ee558f49
|
Merge pull request #107 from jpthu17/fix_2d_RoPE_init_bug
[fix] 2d RoPE init
Former-commit-id: e873ffa66f01268cce600f8da9ad297dc3e8aaaf
|
2024-03-10 10:21:43 +08:00 |
|
jpthu17
|
75938cfaeb
|
[fix] 2d RoPE init
Former-commit-id: ff5931bae6efa94675b9ef6bc25f1b76217d128e
|
2024-03-09 22:04:15 +08:00 |
|
LinB203
|
9a0d0bc843
|
safe dit
Former-commit-id: f407cab7dc0e53257972d430e873f4fd77bb039d
|
2024-03-09 21:53:43 +08:00 |
|
LinB203
|
5ebb382d85
|
xformers and flashattn
Former-commit-id: 002cad95253f7da36344237ce8c8410ffb517711
|
2024-03-09 21:52:03 +08:00 |
|
lb203
|
c08f985c8c
|
Update README.md
Former-commit-id: 6630c22baa2340a8b55badd61472daab7177bc63
|
2024-03-09 21:19:47 +08:00 |
|
lb203
|
c891f85022
|
Merge pull request #106 from jpthu17/add_2d_RoPE
[feat] Add 2D RoPE
Former-commit-id: 85c46fa0e728c9cfc5af4cf6523a7e6a64f96a93
|
2024-03-09 21:18:17 +08:00 |
|
lb203
|
ad54bd8f94
|
Merge pull request #105 from sennnnn/einops_bug
Fix einops bug: module 'keras.backend' has no attribute 'is_tensor'
Former-commit-id: c4f3a3a1172b68a4a34ddfac8ea69be34d11038b
|
2024-03-09 21:13:29 +08:00 |
|
jpthu17
|
aef95b043c
|
[feat] Add 2D RoPE
Former-commit-id: ccae80d339e34fb23706827565b5095ae2c2f320
|
2024-03-09 19:53:48 +08:00 |
|
sennnnn
|
5834bc0a8b
|
Merge branch 'main' into videogpt_deepspeed
Former-commit-id: 04dbc4c5f04d1e82815e02c6215d8ff6e098049f
|
2024-03-09 19:24:12 +08:00 |
|
sennnnn
|
29e167fecf
|
Fix einops bug: module 'keras.backend' has no attribute 'is_tensor'
Former-commit-id: 849f8ed815295bac78c3c10d319e6731aa26ca02
|
2024-03-09 18:18:26 +08:00 |
|
sennnnn
|
efad4348d5
|
Fix config typos.
Former-commit-id: 455973b57bda19379d41e59aa418421fd269281e
|
2024-03-09 17:39:03 +08:00 |
|
sennnnn
|
3b4e881b11
|
Support deepspeed for videogpt training.
Former-commit-id: 1f3dfe038845d91b81b0ecc9b6f3cabb06eed5d5
|
2024-03-09 17:33:30 +08:00 |
|
lb203
|
e415e25897
|
Update README.md
Former-commit-id: 513883df1ad853c9a5e7457c364227261df17a83
|
2024-03-09 17:13:18 +08:00 |
|
lb203
|
e2b563ab2d
|
Merge pull request #91 from RuslanPeresy/typecheck
[refactor] add static type checking
Former-commit-id: 969dfa6dedaeb64cf776d977b466b14568cc4b1c
|
2024-03-09 16:54:19 +08:00 |
|
LinB203
|
6df13b07bb
|
flash-attn train and sample
Former-commit-id: e336565bd5ff2aaf4d0b4ad5f42732e89cd216b3
|
2024-03-09 16:30:09 +08:00 |
|
lb203
|
39e398e815
|
Merge pull request #103 from rain305f/new_eval
[docs]: update the eval code
Former-commit-id: 5ee073e7493a608c27c257b2a341585192c5b68f
|
2024-03-09 15:47:54 +08:00 |
|
rain305f
|
e780368bb6
|
[docs]:update the eval code
Former-commit-id: a8c9e6cb9e39a9e929dab34077280a8d80d85573
|
2024-03-09 06:22:04 +00:00 |
|
rain305f
|
8a987de2a8
|
[docs]:update the eval code
Former-commit-id: 937f2fc87d34ab9d4724cb95a6457b54a6bf4ebc
|
2024-03-09 05:21:43 +00:00 |
|
lb203
|
a60217616e
|
Update README.md
Former-commit-id: 38e0e290e7a5909706c2cce2e4dd047647134fb8
|
2024-03-09 11:49:17 +08:00 |
|
lb203
|
fa401d1d3f
|
Update README.md
Former-commit-id: 88e9f21cfc8ec775dbc9a65f740043e91e26bd91
|
2024-03-09 11:44:12 +08:00 |
|
lb203
|
81f5e207d0
|
Update README.md
Former-commit-id: 826cc5e9162888bed82413088c6be662c278176b
|
2024-03-09 11:41:37 +08:00 |
|
lb203
|
7774b0d1eb
|
Update pyproject.toml
Former-commit-id: 36da5d0e950625e629aebe954f89f92827397d0d
|
2024-03-09 11:37:47 +08:00 |
|
lb203
|
82cc72a739
|
Merge pull request #96 from Jason-fan20/my-docs-branch
Update README.md
Former-commit-id: 426cbdfa78282e098739dc1740d802d8e9c7d6de
|
2024-03-09 10:58:50 +08:00 |
|
lb203
|
39848c3dff
|
Merge pull request #102 from sennnnn/vqvae_data
🐛 [BUG] Fix the memory error bug when loading metadata pickle file of vqvae dataset
Former-commit-id: 3b458d91fdc646e63f004031ebab9984a34934d2
|
2024-03-09 10:58:18 +08:00 |
|
lb203
|
38c2c2ccaf
|
Merge pull request #99 from jialin-zhao/jialin-zhao-xformers-inputs-revised
Update latte.py about the xformers input dims
Former-commit-id: 421b49c351124170ab476e17cba6e45bd7cf706e
|
2024-03-09 09:58:51 +08:00 |
|