13274243a0
Keep K3 suite selection and report-schema scoring in bash, merge K3/vision dataset_args into dpv4 yamls, and pin EvalScope at 735d920ee911 with local patches. Co-authored-by: Cursor <cursoragent@cursor.com>
136 lines
5.0 KiB
TOML
136 lines
5.0 KiB
TOML
[project]
|
|
name = "evalscope"
|
|
dynamic = ["version", "dependencies", "optional-dependencies"]
|
|
description = "EvalScope: Lightweight LLMs Evaluation Framework"
|
|
readme = {file = "README.md", content-type = "text/markdown"}
|
|
license = "Apache-2.0"
|
|
authors = [
|
|
{name = "ModelScope team"},
|
|
{email = "contact@modelscope.cn"}
|
|
]
|
|
keywords = ["python", "llm", "evaluation"]
|
|
requires-python = ">=3.10"
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"Operating System :: OS Independent",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/modelscope/evalscope"
|
|
|
|
[project.scripts]
|
|
evalscope = "evalscope.cli.cli:run_cmd"
|
|
|
|
[build-system]
|
|
requires = ["setuptools>=69", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[tool.setuptools]
|
|
include-package-data = true
|
|
|
|
[tool.setuptools.package-data]
|
|
"evalscope.web" = ["dist/**/*"]
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["."]
|
|
include = ["evalscope*"]
|
|
exclude = ["evalscope.web.node_modules*", "evalscope.web.src*"]
|
|
|
|
[tool.setuptools.dynamic]
|
|
version = {attr = "evalscope.version.__version__"}
|
|
dependencies = {file = ["requirements/framework.txt"]}
|
|
|
|
[tool.setuptools.dynamic.optional-dependencies]
|
|
opencompass = {file = ["requirements/opencompass.txt"]}
|
|
vlmeval = {file = ["requirements/vlmeval.txt"]}
|
|
rag = {file = ["requirements/rag.txt"]}
|
|
perf = {file = ["requirements/perf.txt"]}
|
|
app = {file = ["requirements/app.txt"]}
|
|
aigc = {file = ["requirements/aigc.txt"]}
|
|
sandbox = {file = ["requirements/sandbox.txt"]}
|
|
service = {file = ["requirements/service.txt", "requirements/perf.txt"]}
|
|
mcp = {file = ["requirements/mcp.txt"]}
|
|
dev = {file = ["requirements/dev.txt"]}
|
|
docs = {file = ["requirements/docs.txt"]}
|
|
|
|
ocr_bench = {file = ["evalscope/benchmarks/ocr_bench/requirements.txt"]}
|
|
cc_ocr_v2 = {file = ["evalscope/benchmarks/cc_ocr_v2/requirements.txt"]}
|
|
omnidoc_bench = {file = ["evalscope/benchmarks/omnidoc_bench/legacy/requirements.txt"]}
|
|
olmocr_bench = {file = ["evalscope/benchmarks/olmocr_bench/requirements.txt"]}
|
|
maritime_ocr_bench = {file = ["evalscope/benchmarks/maritime_ocr_bench/requirements.txt"]}
|
|
miniwob = {file = ["evalscope/benchmarks/miniwob/requirements.txt"]}
|
|
ifeval = {file = ["evalscope/benchmarks/ifeval/requirements.txt"]}
|
|
ifbench = {file = ["evalscope/benchmarks/ifbench/requirements.txt"]}
|
|
multi_if = {file = ["evalscope/benchmarks/multi_if/requirements.txt"]}
|
|
olympiad_bench = {file = ["evalscope/benchmarks/olympiad_bench/requirements.txt"]}
|
|
needle_haystack = {file = ["evalscope/benchmarks/needle_haystack/requirements.txt"]}
|
|
openai_mrcr = {file = ["evalscope/benchmarks/openai_mrcr/requirements.txt"]}
|
|
general_arena = {file = ["evalscope/benchmarks/general_arena/requirements.txt"]}
|
|
arena_hard = {file = ["evalscope/benchmarks/arena_hard/requirements.txt"]}
|
|
air_bench = {file = ["evalscope/benchmarks/air_bench/requirements.txt"]}
|
|
caption = {file = ["evalscope/benchmarks/caption/requirements.txt"]}
|
|
refcoco = {file = ["evalscope/benchmarks/refcoco/requirements.txt"]}
|
|
swe_bench = {file = ["evalscope/benchmarks/swe_bench/requirements.txt"]}
|
|
wmt = {file = ["evalscope/benchmarks/wmt/requirements.txt"]}
|
|
torgo = {file = ["evalscope/benchmarks/torgo/requirements.txt"]}
|
|
terminal_bench = {file = ["evalscope/benchmarks/terminal_bench/requirements.txt"]}
|
|
deep_swe = {file = ["evalscope/benchmarks/deep_swe/requirements.txt"]}
|
|
toolathlon = {file = ["evalscope/benchmarks/toolathlon/requirements.txt"]}
|
|
bfcl = {file = ["evalscope/benchmarks/bfcl/requirements.txt"]}
|
|
wide_search = {file = ["evalscope/benchmarks/wide_search/requirements.txt"]}
|
|
vtcbench = {file = ["evalscope/benchmarks/vtcbench/requirements.txt"]}
|
|
all = {file = [
|
|
"requirements/opencompass.txt",
|
|
"requirements/vlmeval.txt",
|
|
"requirements/rag.txt",
|
|
"requirements/perf.txt",
|
|
"requirements/app.txt",
|
|
"requirements/aigc.txt",
|
|
"requirements/service.txt"
|
|
]}
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
python_files = ["*test*.py"]
|
|
python_classes = ["Test*"]
|
|
python_functions = ["test_*"]
|
|
addopts = "-s -v"
|
|
|
|
[tool.ruff]
|
|
include = [
|
|
"pyproject.toml",
|
|
"*.py",
|
|
"evalscope/**/*.py",
|
|
"scripts/release/**/*.py",
|
|
"tests/**/*.py",
|
|
]
|
|
extend-exclude = [
|
|
"docs",
|
|
"examples",
|
|
"evalscope/utils/utils.py",
|
|
"evalscope/third_party",
|
|
"evalscope/backend/rag_eval/clip_benchmark/tasks",
|
|
"evalscope/backend/rag_eval/cmteb/tasks",
|
|
"evalscope/metrics/vision/t2v_metrics",
|
|
]
|
|
force-exclude = true
|
|
line-length = 120
|
|
target-version = "py310"
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "W", "I"]
|
|
ignore = ["E501", "F401"]
|
|
|
|
[tool.ruff.lint.per-file-ignores]
|
|
"tests/**/*.py" = ["E402"]
|
|
|
|
[tool.ruff.format]
|
|
exclude = ["tests/**/*.py"]
|
|
indent-style = "space"
|
|
line-ending = "lf"
|
|
quote-style = "single"
|