transformers/setup.py
Thomas Wolf ba8c4d0ac0
[Dependencies|tokenizers] Make both SentencePiece and Tokenizers optional dependencies (#7659)
* splitting fast and slow tokenizers [WIP]

* [WIP] splitting sentencepiece and tokenizers dependencies

* update dummy objects

* add name_or_path to models and tokenizers

* prefix added to file names

* prefix

* styling + quality

* spliting all the tokenizer files - sorting sentencepiece based ones

* update tokenizer version up to 0.9.0

* remove hard dependency on sentencepiece 🎉

* and removed hard dependency on tokenizers 🎉

* update conversion script

* update missing models

* fixing tests

* move test_tokenization_fast to main tokenization tests - fix bugs

* bump up tokenizers

* fix bert_generation

* update ad fix several tokenizers

* keep sentencepiece in deps for now

* fix funnel and deberta tests

* fix fsmt

* fix marian tests

* fix layoutlm

* fix squeezebert and gpt2

* fix T5 tokenization

* fix xlnet tests

* style

* fix mbart

* bump up tokenizers to 0.9.2

* fix model tests

* fix tf models

* fix seq2seq examples

* fix tests without sentencepiece

* fix slow => fast  conversion without sentencepiece

* update auto and bert generation tests

* fix mbart tests

* fix auto and common test without tokenizers

* fix tests without tokenizers

* clean up tests lighten up when tokenizers + sentencepiece are both off

* style quality and tests fixing

* add sentencepiece to doc/examples reqs

* leave sentencepiece on for now

* style quality split hebert and fix pegasus

* WIP Herbert fast

* add sample_text_no_unicode and fix hebert tokenization

* skip FSMT example test for now

* fix style

* fix fsmt in example tests

* update following Lysandre and Sylvain's comments

* Update src/transformers/testing_utils.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/testing_utils.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/tokenization_utils_base.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/tokenization_utils_base.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2020-10-18 20:51:24 +02:00

153 lines
6.6 KiB
Python

"""
Simple check list from AllenNLP repo: https://github.com/allenai/allennlp/blob/master/setup.py
To create the package for pypi.
1. Change the version in __init__.py, setup.py as well as docs/source/conf.py. Remove the master from the links in
the new models of the README:
(https://huggingface.co/transformers/master/model_doc/ -> https://huggingface.co/transformers/model_doc/)
then run `make fix-copies` to fix the index of the documentation.
2. Unpin specific versions from setup.py that use a git install.
2. Commit these changes with the message: "Release: VERSION"
3. Add a tag in git to mark the release: "git tag VERSION -m'Adds tag VERSION for pypi' "
Push the tag to git: git push --tags origin master
4. Build both the sources and the wheel. Do not change anything in setup.py between
creating the wheel and the source distribution (obviously).
For the wheel, run: "python setup.py bdist_wheel" in the top level directory.
(this will build a wheel for the python version you use to build it).
For the sources, run: "python setup.py sdist"
You should now have a /dist directory with both .whl and .tar.gz source versions.
5. Check that everything looks correct by uploading the package to the pypi test server:
twine upload dist/* -r pypitest
(pypi suggest using twine as other methods upload files via plaintext.)
You may have to specify the repository url, use the following command then:
twine upload dist/* -r pypitest --repository-url=https://test.pypi.org/legacy/
Check that you can install it in a virtualenv by running:
pip install -i https://testpypi.python.org/pypi transformers
6. Upload the final version to actual pypi:
twine upload dist/* -r pypi
7. Copy the release notes from RELEASE.md to the tag in github once everything is looking hunky-dory.
8. Add the release version to docs/source/_static/js/custom.js and .circleci/deploy.sh
9. Update README.md to redirect to correct documentation.
"""
import shutil
from pathlib import Path
from setuptools import find_packages, setup
# Remove stale transformers.egg-info directory to avoid https://github.com/pypa/pip/issues/5466
stale_egg_info = Path(__file__).parent / "transformers.egg-info"
if stale_egg_info.exists():
print(
(
"Warning: {} exists.\n\n"
"If you recently updated transformers to 3.0 or later, this is expected,\n"
"but it may prevent transformers from installing in editable mode.\n\n"
"This directory is automatically generated by Python's packaging tools.\n"
"I will remove it now.\n\n"
"See https://github.com/pypa/pip/issues/5466 for details.\n"
).format(stale_egg_info)
)
shutil.rmtree(stale_egg_info)
extras = {}
extras["ja"] = ["fugashi>=1.0", "ipadic>=1.0.0,<2.0", "unidic_lite>=1.0.7", "unidic>=1.0.2"]
extras["sklearn"] = ["scikit-learn"]
# keras2onnx and onnxconverter-common version is specific through a commit until 1.7.0 lands on pypi
extras["tf"] = [
"tensorflow>=2.0",
"onnxconverter-common",
"keras2onnx"
# "onnxconverter-common @ git+git://github.com/microsoft/onnxconverter-common.git@f64ca15989b6dc95a1f3507ff6e4c395ba12dff5#egg=onnxconverter-common",
# "keras2onnx @ git+git://github.com/onnx/keras-onnx.git@cbdc75cb950b16db7f0a67be96a278f8d2953b48#egg=keras2onnx",
]
extras["tf-cpu"] = [
"tensorflow-cpu>=2.0",
"onnxconverter-common",
"keras2onnx"
# "onnxconverter-common @ git+git://github.com/microsoft/onnxconverter-common.git@f64ca15989b6dc95a1f3507ff6e4c395ba12dff5#egg=onnxconverter-common",
# "keras2onnx @ git+git://github.com/onnx/keras-onnx.git@cbdc75cb950b16db7f0a67be96a278f8d2953b48#egg=keras2onnx",
]
extras["torch"] = ["torch>=1.0"]
extras["onnxruntime"] = ["onnxruntime>=1.4.0", "onnxruntime-tools>=1.4.2"]
extras["serving"] = ["pydantic", "uvicorn", "fastapi", "starlette"]
extras["all"] = extras["serving"] + ["tensorflow", "torch"]
extras["sentencepiece"] = ["sentencepiece!=0.1.92"]
extras["retrieval"] = ["faiss-cpu", "datasets"]
extras["testing"] = ["pytest", "pytest-xdist", "timeout-decorator", "parameterized", "psutil"] + extras["retrieval"]
# sphinx-rtd-theme==0.5.0 introduced big changes in the style.
extras["docs"] = ["recommonmark", "sphinx", "sphinx-markdown-tables", "sphinx-rtd-theme==0.4.3", "sphinx-copybutton"]
extras["quality"] = ["black >= 20.8b1", "isort >= 5.5.4", "flake8 >= 3.8.3"]
extras["dev"] = extras["testing"] + extras["quality"] + extras["ja"] + ["scikit-learn", "tensorflow", "torch", "sentencepiece!=0.1.92"]
setup(
name="transformers",
version="3.3.1",
author="Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Sam Shleifer, Patrick von Platen, Sylvain Gugger, Google AI Language Team Authors, Open AI team Authors, Facebook AI Authors, Carnegie Mellon University Authors",
author_email="thomas@huggingface.co",
description="State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch",
long_description=open("README.md", "r", encoding="utf-8").read(),
long_description_content_type="text/markdown",
keywords="NLP deep learning transformer pytorch tensorflow BERT GPT GPT-2 google openai CMU",
license="Apache",
url="https://github.com/huggingface/transformers",
package_dir={"": "src"},
packages=find_packages("src"),
install_requires=[
"numpy",
"tokenizers == 0.9.2",
# dataclasses for Python versions that don't have it
"dataclasses;python_version<'3.7'",
# utilities from PyPA to e.g. compare versions
"packaging",
# filesystem locks e.g. to prevent parallel downloads
"filelock",
# for downloading models over HTTPS
"requests",
# progress bars in model download and training scripts
"tqdm >= 4.27",
# for OpenAI GPT
"regex != 2019.12.17",
# for SentencePiece models
"sentencepiece != 0.1.92",
"protobuf",
# for XLM
"sacremoses",
],
extras_require=extras,
entry_points={"console_scripts": ["transformers-cli=transformers.commands.transformers_cli:main"]},
python_requires=">=3.6.0",
classifiers=[
"Development Status :: 5 - Production/Stable",
"Intended Audience :: Developers",
"Intended Audience :: Education",
"Intended Audience :: Science/Research",
"License :: OSI Approved :: Apache Software License",
"Operating System :: OS Independent",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.6",
"Programming Language :: Python :: 3.7",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
],
)