lcs2-iiitd / acl-fflm Goto Github PK
View Code? Open in Web Editor NEWCode for our ACL (Findings) Paper - Fingerprinting Fine-tuned Language Models in the wild.
License: MIT License
Code for our ACL (Findings) Paper - Fingerprinting Fine-tuned Language Models in the wild.
License: MIT License
Hi @nirav0999 and other folks, thanks for contributing the code. I was trying to install it to a fresh google colab. After loading all the code and data based on the instruction, I still got some errors when executing requirements.txt. This doesn't seem to block the later training and testing.
%cd ACL-FFLM
!pip3 install -r requirements.txt
... ...
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
yellowbrick 1.5 requires scikit-learn>=1.0.0, but you have scikit-learn 0.24.1 which is incompatible.
xarray 2022.12.0 requires numpy>=1.20, but you have numpy 1.18.5 which is incompatible.
xarray 2022.12.0 requires packaging>=21.3, but you have packaging 20.4 which is incompatible.
xarray 2022.12.0 requires pandas>=1.3, but you have pandas 1.1.4 which is incompatible.
xarray-einstats 0.4.0 requires numpy>=1.20, but you have numpy 1.18.5 which is incompatible.
xarray-einstats 0.4.0 requires scipy>=1.6, but you have scipy 1.4.1 which is incompatible.
torchvision 0.14.1+cu116 requires torch==1.13.1, but you have torch 1.4.0 which is incompatible.
torchtext 0.14.1 requires torch==1.13.1, but you have torch 1.4.0 which is incompatible.
torchaudio 0.13.1+cu116 requires torch==1.13.1, but you have torch 1.4.0 which is incompatible.
tifffile 2022.10.10 requires numpy>=1.19.2, but you have numpy 1.18.5 which is incompatible.
tables 3.7.0 requires numpy>=1.19.0, but you have numpy 1.18.5 which is incompatible.
pymc 4.1.4 requires cachetools>=4.2.1, but you have cachetools 4.1.1 which is incompatible.
pydata-google-auth 1.4.0 requires google-auth<3.0dev,>=1.25.0; python_version >= "3.6", but you have google-auth 1.23.0 which is incompatible.
proto-plus 1.22.1 requires protobuf<5.0.0dev,>=3.19.0, but you have protobuf 3.13.0 which is incompatible.
plotnine 0.8.0 requires numpy>=1.19.0, but you have numpy 1.18.5 which is incompatible.
plotnine 0.8.0 requires scipy>=1.5.0, but you have scipy 1.4.1 which is incompatible.
pathy 0.10.1 requires smart-open<7.0.0,>=5.2.1, but you have smart-open 3.0.0 which is incompatible.
pandas-gbq 0.17.9 requires google-auth>=1.25.0, but you have google-auth 1.23.0 which is incompatible.
pandas-gbq 0.17.9 requires pyarrow<10.0dev,>=3.0.0, but you have pyarrow 2.0.0 which is incompatible.
jaxlib 0.3.25+cuda11.cudnn805 requires numpy>=1.20, but you have numpy 1.18.5 which is incompatible.
jaxlib 0.3.25+cuda11.cudnn805 requires scipy>=1.5, but you have scipy 1.4.1 which is incompatible.
jax 0.3.25 requires numpy>=1.20, but you have numpy 1.18.5 which is incompatible.
jax 0.3.25 requires scipy>=1.5, but you have scipy 1.4.1 which is incompatible.
gym 0.25.2 requires importlib-metadata>=4.8.0; python_version < "3.10", but you have importlib-metadata 2.0.0 which is incompatible.
grpcio-status 1.48.2 requires grpcio>=1.48.2, but you have grpcio 1.33.2 which is incompatible.
googleapis-common-protos 1.57.1 requires protobuf!=3.20.0,!=3.20.1,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.19.5, but you have protobuf 3.13.0 which is incompatible.
google-colab 1.0.0 requires requests>=2.25.1, but you have requests 2.25.0 which is incompatible.
google-cloud-translate 3.8.4 requires protobuf!=3.20.0,!=3.20.1,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.19.5, but you have protobuf 3.13.0 which is incompatible.
google-cloud-storage 2.7.0 requires google-auth<3.0dev,>=1.25.0, but you have google-auth 1.23.0 which is incompatible.
google-cloud-language 2.6.1 requires protobuf!=3.20.0,!=3.20.1,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.19.5, but you have protobuf 3.13.0 which is incompatible.
google-cloud-firestore 2.7.3 requires protobuf!=3.20.0,!=3.20.1,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.19.5, but you have protobuf 3.13.0 which is incompatible.
google-cloud-datastore 2.11.1 requires protobuf!=3.20.0,!=3.20.1,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.19.5, but you have protobuf 3.13.0 which is incompatible.
google-cloud-core 2.3.2 requires google-auth<3.0dev,>=1.25.0, but you have google-auth 1.23.0 which is incompatible.
google-cloud-bigquery 3.4.1 requires grpcio<2.0dev,>=1.47.0, but you have grpcio 1.33.2 which is incompatible.
google-cloud-bigquery 3.4.1 requires protobuf!=3.20.0,!=3.20.1,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.19.5, but you have protobuf 3.13.0 which is incompatible.
google-cloud-bigquery-storage 2.17.0 requires protobuf!=3.20.0,!=3.20.1,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.19.5, but you have protobuf 3.13.0 which is incompatible.
google-api-core 2.11.0 requires google-auth<3.0dev,>=2.14.1, but you have google-auth 1.23.0 which is incompatible.
google-api-core 2.11.0 requires protobuf!=3.20.0,!=3.20.1,!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.19.5, but you have protobuf 3.13.0 which is incompatible.
fastai 2.7.10 requires torch<1.14,>=1.7, but you have torch 1.4.0 which is incompatible.
db-dtypes 1.0.5 requires pyarrow>=3.0.0, but you have pyarrow 2.0.0 which is incompatible.
confection 0.0.3 requires srsly<3.0.0,>=2.4.0, but you have srsly 1.0.5 which is incompatible.
cmdstanpy 1.0.8 requires numpy>=1.21, but you have numpy 1.18.5 which is incompatible.
Successfully installed Keras-2.4.3 Markdown-3.3.3 Pillow-8.0.1 PyYAML-5.3.1 absl-py-0.11.0 blis-0.7.4 boto3-1.16.14 botocore-1.19.14 cachetools-4.1.1 catalogue-1.0.0 certifi-2020.11.8 chardet-3.0.4 cycler-0.10.0 cymem-2.0.5 datasets-1.1.2 dill-0.3.3 en-core-web-sm-2.3.1 filelock-3.0.12 future-0.18.2 gast-0.3.3 gensim-3.8.3 google-auth-1.23.0 google-auth-oauthlib-0.4.2 grpcio-1.33.2 h5py-2.10.0 hypopt-1.0.9 importlib-metadata-2.0.0 jmespath-0.10.0 joblib-0.17.0 jsonlines-1.2.0 kiwisolver-1.3.1 matplotlib-3.3.2 multiprocess-0.70.11.1 murmurhash-1.0.5 nltk-3.5 numpy-1.18.5 oauthlib-3.1.0 packaging-20.4 pandas-1.1.4 plac-1.1.3 preshed-3.0.5 protobuf-3.13.0 pyarrow-2.0.0 pyparsing-2.4.7 python-dateutil-2.8.1 pytz-2020.4 readability-0.3.1 regex-2020.10.28 requests-2.25.0 requests-oauthlib-1.3.0 rsa-4.6 s3transfer-0.3.3 sacremoses-0.0.43 scikit-learn-0.24.1 scipy-1.4.1 sentencepiece-0.1.91 sklearn-0.0 smart-open-3.0.0 sortedcontainers-2.3.0 spacy-2.3.5 srsly-1.0.5 tensorboard-2.3.0 tensorboard-plugin-wit-1.7.0 tensorflow-2.3.1 tensorflow-estimator-2.3.0 tensorflow-gpu-2.3.1 termcolor-1.1.0 thinc-7.4.5 threadpoolctl-2.1.0 tokenizers-0.9.2 torch-1.4.0 tqdm-4.49.0 urllib3-1.25.11 wasabi-0.8.0 wget-3.2 wrapt-1.12.1 writeprints-0.2.1 xgboost-1.2.1 xxhash-2.0.0 zipp-3.4.0
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.