pyproject.toml

[build-system]
requires = ["setuptools>=40.8.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "lm_eval"
version = "0.4.0"
authors = [
    {name="EleutherAI", email="contact@eleuther.ai"}
]
description = "A framework for evaluating language models"
readme = "README.md"
classifiers = [
    "Development Status :: 3 - Alpha",
    "Programming Language :: Python :: 3",
    "License :: OSI Approved :: MIT License",
    "Operating System :: OS Independent",
]
requires-python = ">=3.8"
license = { "text" = "MIT" }
dependencies = [
    "accelerate>=0.21.0",
    "evaluate",
    "datasets>=2.0.0",
    "evaluate>=0.4.0",
    "jsonlines",
    "numexpr",
    "peft>=0.2.0",
    "pybind11>=2.6.2",
    "pytablewriter",
    "rouge-score>=0.0.4",
    "sacrebleu>=1.5.0",
    "scikit-learn>=0.24.1",
    "sqlitedict",
    "torch>=1.8",
    "tqdm-multiprocess",
    "transformers>=4.1",
    "zstandard",
]

[tool.setuptools.packages.find]
include = ["lm_eval*"]

# required to include yaml files in pip installation
[tool.setuptools.package-data]
lm_eval = ["**/*.yaml", "tasks/**/*"]

[project.scripts]
lm-eval = "lm_eval.__main__:cli_evaluate"
lm_eval = "lm_eval.__main__:cli_evaluate"

[project.urls]
Homepage = "https://github.com/EleutherAI/lm-evaluation-harness"
Repository = "https://github.com/EleutherAI/lm-evaluation-harness"

[project.optional-dependencies]
anthropic = ["anthropic"]
dev = ["pytest", "pytest-cov", "pytest-xdist", "pre-commit", "mypy"]
gptq = ["auto-gptq[triton] @ git+https://github.com/PanQiWei/AutoGPTQ"]
ifeval = ["langdetect", "immutabledict"]
mamba = ["mamba_ssm", "causal-conv1d==1.0.2"]
math = ["sympy>=1.12", "antlr4-python3-runtime==4.11"]
multilingual = ["nagisa>=0.2.7", "jieba>=0.42.1", "pycountry"]
openai = ["openai==1.3.9", "tiktoken"]
promptsource = [
    "promptsource @ git+https://github.com/bigscience-workshop/promptsource.git#egg=promptsource"
]
sentencepiece = ["sentencepiece>=0.1.98", "protobuf>=4.22.1"]
testing = ["pytest", "pytest-cov", "pytest-xdist"]
vllm = ["vllm<=0.2.5"]
zeno = ["pandas", "zeno-client"]
all = [
    "lm_eval[anthropic]",
    "lm_eval[dev]",
    "lm_eval[gptq]",
    "lm_eval[ifeval]",
    "lm_eval[linting]",
    "lm_eval[mamba]",
    "lm_eval[math]",
    "lm_eval[multilingual]",
    "lm_eval[openai]",
    "lm_eval[promptsource]",
    "lm_eval[sentencepiece]",
    "lm_eval[testing]",
    "lm_eval[vllm]",
    "lm_eval[zeno]",
]

[tool.ruff]
extend-exclude = ["lm_eval/evaluator.py", "lm_eval/tasks/*.py"]

[tool.ruff.lint]
extend-select = ["I"]

[tool.ruff.isort]
lines-after-imports = 2
known-first-party = ["lm_eval"]

[tool.ruff.extend-per-file-ignores]
"__init__.py" = ["F401","F402","F403","I"]
"lm_eval/tasks/*"= ["E721"]