deepseekmirror/DeepSeek-VL2
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-VL2.git synced 2025-04-19 10:09:09 -04:00
Code Issues Actions Packages Projects Releases Wiki Activity
33 Commits 1 Branch 0 Tags 32 MiB
fa99a32471
Commit Graph

33 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Abubakar Sattar
fa99a32471
Merge 8c69318fc7 into ef9f91e2b6 2025-02-28 14:41:54 +00:00
StevenLiuWen
ef9f91e2b6 Update README.md 2025-02-26 13:03:37 +08:00
StevenLiuWen
699e00ad0d Update utils.py 2025-02-26 13:00:15 +08:00
StevenLiuWen
3c2cd21c9f
Merge pull request #89 from CUHKSZzxy/optimize-deps 
change xformers import location
 2025-02-20 14:39:09 +08:00
zxy
b6e557c73e recover attrdict 2025-02-19 19:30:58 +08:00
zxy
cf21982aa5 optimize lib dependencies 2025-02-19 13:46:33 +08:00
Zizheng Pan
32d92585ed
Update demo link 2025-02-09 18:01:06 +08:00
StevenLiuWen
a698c36a4c Update README.md 2025-02-06 00:04:05 +08:00
StevenLiuWen
a667810e3c Update README.md 2025-02-06 00:02:05 +08:00
StevenLiuWen
6eedfe3877 add huggingface space demo 2025-02-05 19:50:10 +08:00
StevenLiuWen
0b05daf3d2 Update web_demo.py 2025-02-05 19:23:13 +08:00
StevenLiuWen
c10e7eba36 update requirements.txt 2025-02-04 19:31:10 +08:00
StevenLiuWen
0dae143493 Update inference.py 2025-02-04 19:11:34 +08:00
Abubakar Sattar
8c69318fc7
Fixed a typo in Update inference.py 
Fixed a typo in Update inference.py

Prefilling was misspelled here.

parser.add_argument("--chunk_size", type=int, default=-1,
                        help="chunk size for the model for prefiiling. "
                             "When using 40G gpu for vl2-small, set a chunk_size for incremental_prefilling."
                             "Otherwise, default value is -1, which means we do not use incremental_prefilling.")
 2025-01-29 14:53:43 +05:00
charlescxk
c74816ad22 fix typo 2025-01-29 16:02:52 +08:00
StevenLiuWen
ff23960c5c Update siglip_vit.py 2025-01-16 11:25:10 +08:00
StevenLiuWen
9dd177671e
Merge pull request #34 from Isotr0py/main 
Fix flash_attn import in siglip_vit
 2025-01-16 11:13:08 +08:00
Xiaokang Chen
df7a47c57e
Update pyproject.toml 2025-01-16 11:11:14 +08:00
Xiaokang Chen
59640c1ccb
Update pyproject.toml 2025-01-16 11:08:12 +08:00
Isotr0py
a60e8208bb fix flash_attn import on old GPU 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-01-10 01:55:19 +08:00
StevenLiuWen
66ec91081c Update inference.py 2024-12-30 14:48:51 +08:00
StevenLiuWen
9789f97283 remove clear_cuda_cache in forward 2024-12-30 14:19:34 +08:00
StevenLiuWen
a8341f36dd Update README.md 2024-12-26 22:38:45 +08:00
StevenLiuWen
faf18023f2 update 
Gradio Demo Example, Incremental Prefilling and VLMEvalKit Support
 2024-12-26 22:37:57 +08:00
Zizheng Pan
8bde1c1ae1 update readme and repo dependency 2024-12-18 19:54:05 +08:00
Xingchao Liu
cd4bb743e2 fix example 2024-12-18 17:57:47 +08:00
Xingchao Liu
6036493d83 change module name to deepseek_vl2 2024-12-17 15:42:09 +08:00
StevenLiuWen
7caa51a05c Merge branch 'main' of https://github.com/deepseek-ai/DeepSeek-VL2 2024-12-16 22:15:49 +08:00
StevenLiuWen
90b3b796ab Update simsun.ttc 2024-12-16 22:15:45 +08:00
XCL
2a99af7eea
Merge pull request #6 from li-plus/fix-demo 
Fix example code in README
 2024-12-16 15:21:46 +08:00
Jiahao Li
85cdab0f5f Fix example code in README 2024-12-16 14:46:55 +08:00
Xingchao Liu
b3a4b9bbdd update arxiv link and bibtex 2024-12-16 10:39:34 +08:00
Xingchao Liu
d527122a4d Initial commit 2024-12-13 20:38:59 +08:00