Comments (1)
After the above, I'm able to run Kosmos-2.5 on a single RTX3090 Windows 11 PC via WSL-Ubuntu. I created (and am closing) this issue in case anyone is facing the same errors and thus may benefit from my experience above.
If you're facing any Python package issues, Python v3.10.12 worked for me and my entire requirements.txt looks as below. Feel free to reach out if you think I can help in any way:
antlr4-python3-runtime==4.8
attrs==21.2.0
Automat==20.2.0
bcrypt==3.2.0
blinker==1.4
boto==2.49.0
boto3==1.34.140
botocore==1.34.140
Brotli==1.0.9
certifi==2020.6.20
cffi==1.16.0
chardet==4.0.0
charset-normalizer==3.3.2
click==8.0.3
colorama==0.4.4
command-not-found==0.3
constantly==15.1.0
cryptography==3.4.8
cupshelpers==1.0
Cython==3.0.10
dbus-python==1.2.18
defer==1.0.6
deluge==2.0.3
distro==1.7.0
distro-info==1.1+ubuntu0.2
einops==0.8.0
fairscale==0.4.0
fairseq @ git+https://github.com/Dod-o/kosmos2.5_tools.git@ec5dc5a2523a58bd8172519a4f5820c637bb22fd
filelock==3.13.1
flash-attn @ file:///home/abheekg/Downloads/flash-attention
fsspec==2024.6.1
GeoIP==1.3.2
httplib2==0.20.2
huggingface-hub==0.23.4
hydra-core==1.0.7
hyperlink==21.0.0
idna==3.3
importlib-metadata==4.6.4
incremental==21.3.0
infinibatch @ git+https://github.com/Dod-o/kosmos2.5_tools.git@aea555a721d701ec3b81c41c3d59b54dc28ced23
iopath==0.1.10
jeepney==0.7.1
Jinja2==3.1.4
jmespath==1.0.1
keyring==23.5.0
language-selector==0.1
launchpadlib==1.10.16
lazr.restfulclient==0.14.4
lazr.uri==1.0.6
libtorrent===2.0.5-build-libtorrent-rasterbar-qrM5vM-libtorrent-rasterbar-2.0.5-bindings-python
lxml==5.2.2
macaroonbakery==1.3.1
Mako==1.1.3
MarkupSafe==2.0.1
more-itertools==8.10.0
mpmath==1.3.0
mutagen==1.45.1
netifaces==0.11.0
networkx==3.3
ninja==1.11.1
numpy==1.22.0
nvidia-cublas-cu12==12.4.2.65
nvidia-cuda-cupti-cu12==12.4.99
nvidia-cuda-nvrtc-cu12==12.4.99
nvidia-cuda-runtime-cu12==12.4.99
nvidia-cudnn-cu12==9.1.0.70
nvidia-cufft-cu12==11.2.0.44
nvidia-curand-cu12==10.3.5.119
nvidia-cusolver-cu12==11.6.0.99
nvidia-cusparse-cu12==12.3.0.142
nvidia-nccl-cu12==2.21.5
nvidia-nvjitlink-cu12==12.4.99
nvidia-nvtx-cu12==12.4.99
oauthlib==3.2.0
olefile==0.46
omegaconf==2.0.6
packaging==24.1
Pillow==9.0.1
portalocker==2.10.0
protobuf==3.12.4
psutil==6.0.0
pyasn1==0.4.8
pyasn1-modules==0.2.1
pycairo==1.20.1
pycparser==2.22
pycryptodomex==3.11.0
pycups==2.0.1
pygame==2.1.2
PyGObject==3.42.1
PyHamcrest==2.0.2
PyJWT==2.3.0
pymacaroons==0.13.0
PyNaCl==1.5.0
pyOpenSSL==21.0.0
pyparsing==2.4.7
pyRFC3339==1.1
python-apt==2.4.0+ubuntu3
python-dateutil==2.9.0.post0
pytorch-triton==3.0.0+dedb7bdf33
pytz==2022.1
pyxattr==0.7.2
pyxdg==0.27
PyYAML==5.4.1
regex==2024.5.15
rencode==1.0.6
requests==2.32.3
s3transfer==0.10.2
sacrebleu==2.4.2
safetensors==0.4.3
scipy==1.10.0
SecretStorage==3.3.1
service-identity==18.1.0
setproctitle==1.2.2
six==1.16.0
sympy==1.12.1
systemd-python==234
tabulate==0.9.0
tiktoken==0.7.0
timm==0.4.12
tokenizers==0.13.3
torch==2.5.0.dev20240705+cu124
torchaudio==2.4.0.dev20240705+cu124
torchscale @ git+https://github.com/Dod-o/kosmos2.5_tools.git@a0275c11a1de798e342c9dde34a3752fd2984719
torchvision==0.20.0.dev20240705+cu124
tqdm==4.66.4
transformers @ git+https://github.com/Dod-o/kosmos2.5_tools.git@b7b7e7cab86931c46890376b5fd02d53ea36da67
triton==2.3.1
Twisted==22.1.0
typing_extensions==4.12.2
ubuntu-pro-client==8001
ufw==0.36.1
unattended-upgrades==0.1
urllib3==1.26.5
wadllib==1.3.6
websockets==9.1
xdg==5
xformers @ git+https://github.com/facebookresearch/xformers.git@04de99bb28aa6de8d48fab3cdbbc9e3874c994b8
yt-dlp==2022.4.8
zipp==1.0.0
zope.interface==5.4.0
from unilm.
Related Issues (20)
- How to fine-tune E5-mistral-7b-instruct? HOT 1
- Kosmo2.5 Chinese performance very bad HOT 2
- why last_hidden_states.sequence_length is not same as input_ids.sequence_length
- Model for commercial use? HOT 1
- Kosmos 2.5 for Volta GPU
- The influence of t (temperature) in the E5 Model paper HOT 4
- (BEIT-3) I can't find transformers.py HOT 3
- Kosmos-2.5 Dependencies Should Be Updated HOT 1
- The pretraining code and model of beit3
- TROCR model weight file cannot be downloaded.
- BEIT3 RuntimeError: Size mismatch when loading checkpoint for BEiT3ForRetrieval model
- [BEIT-3] error happens when I evaluate BEiT-3 finetuned model on VQAv2 HOT 4
- Missing Documentation
- Kosmos 2.5 dataset availability
- Kosmos-2.5 - Image-to-markdown generation for images outside the sample-set provided is almost entirely garbled - output markdown is completely unusable.
- Kosmos-2.5 - Python version 3.10.x (and any other confirmed working versions) should be mentioned as a requirement to deploy & infer the Kosmos-2.5 model
- Kosmos-2 batch modality and processing speed
- how to resume training for layoutlmv3-publaynet
- TextDiffuser - SD2.1 code and weights
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from unilm.