Spaces:
Running
Running
File size: 15,943 Bytes
455a40f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 |
# Copyright 2021 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
Simple check list from AllenNLP repo: https://github.com/allenai/allennlp/blob/main/setup.py
To create the package for pypi.
1. Run `make pre-release` (or `make pre-patch` for a patch release) then run `make fix-copies` to fix the index of the
documentation.
If releasing on a special branch, copy the updated README.md on the main branch for your the commit you will make
for the post-release and run `make fix-copies` on the main branch as well.
2. Run Tests for Amazon Sagemaker. The documentation is located in `./tests/sagemaker/README.md`, otherwise @philschmid.
3. Unpin specific versions from setup.py that use a git install.
4. Checkout the release branch (v<RELEASE>-release, for example v4.19-release), and commit these changes with the
message: "Release: <VERSION>" and push.
5. Wait for the tests on main to be completed and be green (otherwise revert and fix bugs)
6. Add a tag in git to mark the release: "git tag v<VERSION> -m 'Adds tag v<VERSION> for pypi' "
Push the tag to git: git push --tags origin v<RELEASE>-release
7. Build both the sources and the wheel. Do not change anything in setup.py between
creating the wheel and the source distribution (obviously).
Clean up your build and dist folders (to avoid re-uploading oldies):
rm -rf dist
rm -rf build
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.
8. Check that everything looks correct by uploading the package to the pypi test server:
twine upload dist/* -r testpypi
(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 testpypi --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
Check you can run the following commands:
python -c "from transformers import pipeline; classifier = pipeline('text-classification'); print(classifier('What a nice release'))"
python -c "from transformers import *"
If making a patch release, double check the bug you are patching is indeed resolved.
9. Upload the final version to actual pypi:
twine upload dist/* -r pypi
10. Copy the release notes from RELEASE.md to the tag in github once everything is looking hunky-dory.
11. Run `make post-release` then run `make fix-copies`. If you were on a branch for the release,
you need to go back to main before executing this.
"""
import os
import re
import shutil
from pathlib import Path
from setuptools import Command, 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)
# IMPORTANT:
# 1. all dependencies should be listed here with their version requirements if any
# 2. once modified, run: `make deps_table_update` to update src/transformers/dependency_versions_table.py
_deps = [
"Pillow",
"accelerate>=0.10.0",
"av==9.2.0", # Latest version of PyAV (10.0.0) has issues with audio stream.
"beautifulsoup4",
"black~=23.1",
"codecarbon==1.2.0",
"cookiecutter==1.7.3",
"dataclasses",
"datasets!=2.5.0",
"decord==0.6.0",
"deepspeed>=0.8.3",
"dill<0.3.5",
"evaluate>=0.2.0",
"fairscale>0.3",
"faiss-cpu",
"fastapi",
"filelock",
"flax>=0.4.1",
"ftfy",
"fugashi>=1.0",
"GitPython<3.1.19",
"hf-doc-builder>=0.3.0",
"huggingface-hub>=0.11.0,<1.0",
"importlib_metadata",
"ipadic>=1.0.0,<2.0",
"isort>=5.5.4",
"jax>=0.2.8,!=0.3.2,<=0.3.6",
"jaxlib>=0.1.65,<=0.3.6",
"jieba",
"kenlm",
"keras-nlp>=0.3.1",
"librosa",
"nltk",
"natten>=0.14.6",
"numpy>=1.17",
"onnxconverter-common",
"onnxruntime-tools>=1.4.2",
"onnxruntime>=1.4.0",
"optuna",
"optax>=0.0.8",
"packaging>=20.0",
"parameterized",
"phonemizer",
"protobuf<=3.20.2",
"psutil",
"pyyaml>=5.1",
"pydantic",
"pytest",
"pytest-timeout",
"pytest-xdist",
"python>=3.7.0",
"ray[tune]",
"regex!=2019.12.17",
"requests",
"rhoknp>=1.1.0",
"rjieba",
"rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1",
"ruff>=0.0.241,<=0.0.259",
"sacrebleu>=1.4.12,<2.0.0",
"sacremoses",
"safetensors>=0.2.1",
"sagemaker>=2.31.0",
"scikit-learn",
"sentencepiece>=0.1.91,!=0.1.92",
"sigopt",
"starlette",
"sudachipy>=0.6.6",
"sudachidict_core>=20220729",
# TensorFlow pin. When changing this value, update examples/tensorflow/_tests_requirements.txt accordingly
"tensorflow-cpu>=2.4,<2.13",
"tensorflow>=2.4,<2.13",
"tensorflow-text<2.13",
"tf2onnx",
"timeout-decorator",
"timm",
"tokenizers>=0.11.1,!=0.11.3,<0.14",
"torch>=1.9,!=1.12.0",
"torchaudio",
"torchvision",
"pyctcdecode>=0.4.0",
"tqdm>=4.27",
"unidic>=1.0.2",
"unidic_lite>=1.0.7",
"uvicorn",
]
# this is a lookup table with items like:
#
# tokenizers: "tokenizers==0.9.4"
# packaging: "packaging"
#
# some of the values are versioned whereas others aren't.
deps = {b: a for a, b in (re.findall(r"^(([^!=<>~ ]+)(?:[!=<>~ ].*)?$)", x)[0] for x in _deps)}
# since we save this data in src/transformers/dependency_versions_table.py it can be easily accessed from
# anywhere. If you need to quickly access the data from this table in a shell, you can do so easily with:
#
# python -c 'import sys; from transformers.dependency_versions_table import deps; \
# print(" ".join([ deps[x] for x in sys.argv[1:]]))' tokenizers datasets
#
# Just pass the desired package names to that script as it's shown with 2 packages above.
#
# If transformers is not yet installed and the work is done from the cloned repo remember to add `PYTHONPATH=src` to the script above
#
# You can then feed this for example to `pip`:
#
# pip install -U $(python -c 'import sys; from transformers.dependency_versions_table import deps; \
# print(" ".join([deps[x] for x in sys.argv[1:]]))' tokenizers datasets)
#
def deps_list(*pkgs):
return [deps[pkg] for pkg in pkgs]
class DepsTableUpdateCommand(Command):
"""
A custom distutils command that updates the dependency table.
usage: python setup.py deps_table_update
"""
description = "build runtime dependency table"
user_options = [
# format: (long option, short option, description).
("dep-table-update", None, "updates src/transformers/dependency_versions_table.py"),
]
def initialize_options(self):
pass
def finalize_options(self):
pass
def run(self):
entries = "\n".join([f' "{k}": "{v}",' for k, v in deps.items()])
content = [
"# THIS FILE HAS BEEN AUTOGENERATED. To update:",
"# 1. modify the `_deps` dict in setup.py",
"# 2. run `make deps_table_update``",
"deps = {",
entries,
"}",
"",
]
target = "src/transformers/dependency_versions_table.py"
print(f"updating {target}")
with open(target, "w", encoding="utf-8", newline="\n") as f:
f.write("\n".join(content))
extras = {}
extras["ja"] = deps_list("fugashi", "ipadic", "unidic_lite", "unidic", "sudachipy", "sudachidict_core", "rhoknp")
extras["sklearn"] = deps_list("scikit-learn")
extras["tf"] = deps_list("tensorflow", "onnxconverter-common", "tf2onnx", "tensorflow-text", "keras-nlp")
extras["tf-cpu"] = deps_list("tensorflow-cpu", "onnxconverter-common", "tf2onnx", "tensorflow-text", "keras-nlp")
extras["torch"] = deps_list("torch")
extras["accelerate"] = deps_list("accelerate")
if os.name == "nt": # windows
extras["retrieval"] = deps_list("datasets") # faiss is not supported on windows
extras["flax"] = [] # jax is not supported on windows
else:
extras["retrieval"] = deps_list("faiss-cpu", "datasets")
extras["flax"] = deps_list("jax", "jaxlib", "flax", "optax")
extras["tokenizers"] = deps_list("tokenizers")
extras["ftfy"] = deps_list("ftfy")
extras["onnxruntime"] = deps_list("onnxruntime", "onnxruntime-tools")
extras["onnx"] = deps_list("onnxconverter-common", "tf2onnx") + extras["onnxruntime"]
extras["modelcreation"] = deps_list("cookiecutter")
extras["sagemaker"] = deps_list("sagemaker")
extras["deepspeed"] = deps_list("deepspeed") + extras["accelerate"]
extras["fairscale"] = deps_list("fairscale")
extras["optuna"] = deps_list("optuna")
extras["ray"] = deps_list("ray[tune]")
extras["sigopt"] = deps_list("sigopt")
extras["integrations"] = extras["optuna"] + extras["ray"] + extras["sigopt"]
extras["serving"] = deps_list("pydantic", "uvicorn", "fastapi", "starlette")
extras["audio"] = deps_list("librosa", "pyctcdecode", "phonemizer", "kenlm")
# `pip install ".[speech]"` is deprecated and `pip install ".[torch-speech]"` should be used instead
extras["speech"] = deps_list("torchaudio") + extras["audio"]
extras["torch-speech"] = deps_list("torchaudio") + extras["audio"]
extras["tf-speech"] = extras["audio"]
extras["flax-speech"] = extras["audio"]
extras["vision"] = deps_list("Pillow")
extras["timm"] = deps_list("timm")
extras["torch-vision"] = deps_list("torchvision") + extras["vision"]
extras["natten"] = deps_list("natten")
extras["codecarbon"] = deps_list("codecarbon")
extras["video"] = deps_list("decord", "av")
extras["sentencepiece"] = deps_list("sentencepiece", "protobuf")
extras["testing"] = (
deps_list(
"pytest",
"pytest-xdist",
"timeout-decorator",
"parameterized",
"psutil",
"datasets",
"dill",
"evaluate",
"pytest-timeout",
"black",
"sacrebleu",
"rouge-score",
"nltk",
"GitPython",
"hf-doc-builder",
"protobuf", # Can be removed once we can unpin protobuf
"sacremoses",
"rjieba",
"safetensors",
"beautifulsoup4",
)
+ extras["retrieval"]
+ extras["modelcreation"]
)
extras["deepspeed-testing"] = extras["deepspeed"] + extras["testing"] + extras["optuna"] + extras["sentencepiece"]
extras["quality"] = deps_list("black", "datasets", "isort", "ruff", "GitPython", "hf-doc-builder")
extras["all"] = (
extras["tf"]
+ extras["torch"]
+ extras["flax"]
+ extras["sentencepiece"]
+ extras["tokenizers"]
+ extras["torch-speech"]
+ extras["vision"]
+ extras["integrations"]
+ extras["timm"]
+ extras["torch-vision"]
+ extras["codecarbon"]
+ extras["accelerate"]
+ extras["video"]
)
# Might need to add doc-builder and some specific deps in the future
extras["docs_specific"] = ["hf-doc-builder"]
# "docs" needs "all" to resolve all the references
extras["docs"] = extras["all"] + extras["docs_specific"]
extras["dev-torch"] = (
extras["testing"]
+ extras["torch"]
+ extras["sentencepiece"]
+ extras["tokenizers"]
+ extras["torch-speech"]
+ extras["vision"]
+ extras["integrations"]
+ extras["timm"]
+ extras["torch-vision"]
+ extras["codecarbon"]
+ extras["quality"]
+ extras["ja"]
+ extras["docs_specific"]
+ extras["sklearn"]
+ extras["modelcreation"]
+ extras["onnxruntime"]
)
extras["dev-tensorflow"] = (
extras["testing"]
+ extras["tf"]
+ extras["sentencepiece"]
+ extras["tokenizers"]
+ extras["vision"]
+ extras["quality"]
+ extras["docs_specific"]
+ extras["sklearn"]
+ extras["modelcreation"]
+ extras["onnx"]
+ extras["tf-speech"]
)
extras["dev"] = (
extras["all"]
+ extras["testing"]
+ extras["quality"]
+ extras["ja"]
+ extras["docs_specific"]
+ extras["sklearn"]
+ extras["modelcreation"]
)
extras["torchhub"] = deps_list(
"filelock",
"huggingface-hub",
"importlib_metadata",
"numpy",
"packaging",
"protobuf",
"regex",
"requests",
"sentencepiece",
"torch",
"tokenizers",
"tqdm",
)
# when modifying the following list, make sure to update src/transformers/dependency_versions_check.py
install_requires = [
deps["importlib_metadata"] + ";python_version<'3.8'", # importlib_metadata for Python versions that don't have it
deps["filelock"], # filesystem locks, e.g., to prevent parallel downloads
deps["huggingface-hub"],
deps["numpy"],
deps["packaging"], # utilities from PyPA to e.g., compare versions
deps["pyyaml"], # used for the model cards metadata
deps["regex"], # for OpenAI GPT
deps["requests"], # for downloading models over HTTPS
deps["tokenizers"],
deps["tqdm"], # progress bars in model download and training scripts
]
setup(
name="transformers",
version="4.28.0", # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
author="The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/transformers/graphs/contributors)",
author_email="transformers@huggingface.co",
description="State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow",
long_description=open("README.md", "r", encoding="utf-8").read(),
long_description_content_type="text/markdown",
keywords="NLP vision speech deep learning transformer pytorch tensorflow jax BERT GPT-2 Wav2Vec2 ViT",
license="Apache 2.0 License",
url="https://github.com/huggingface/transformers",
package_dir={"": "src"},
packages=find_packages("src"),
include_package_data=True,
package_data={"transformers": ["*.cu", "*.cpp", "*.cuh", "*.h", "*.pyx"]},
zip_safe=False,
extras_require=extras,
entry_points={"console_scripts": ["transformers-cli=transformers.commands.transformers_cli:main"]},
python_requires=">=3.7.0",
install_requires=install_requires,
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 :: 3.7",
"Programming Language :: Python :: 3.8",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
],
cmdclass={"deps_table_update": DepsTableUpdateCommand},
)
|