Metadata-Version: 2.1
Name: crfm-helm
Version: 0.2.4
Summary: Benchmark for language models
Home-page: https://github.com/stanford-crfm/helm
Author: Stanford CRFM
Author-email: contact-crfm@stanford.edu
License: Apache License 2.0
Keywords: language models benchmarking
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.8
Classifier: License :: OSI Approved :: Apache Software License
Requires-Python: ~=3.8
License-File: LICENSE
Requires-Dist: cattrs~=22.2.0
Requires-Dist: dacite~=1.6.0
Requires-Dist: importlib-resources~=5.10.0
Requires-Dist: Mako~=1.2.3
Requires-Dist: numpy~=1.23.3
Requires-Dist: pyhocon~=0.3.59
Requires-Dist: retrying~=1.3.4
Requires-Dist: spacy~=3.5.3
Requires-Dist: tqdm~=4.64.1
Requires-Dist: zstandard~=0.18.0
Requires-Dist: sqlitedict~=1.7.0
Requires-Dist: bottle~=0.12.23
Requires-Dist: protobuf~=3.20.2
Requires-Dist: pymongo~=4.2.0
Requires-Dist: datasets~=2.5.2
Requires-Dist: pyarrow>=11.0.0
Requires-Dist: nltk~=3.7
Requires-Dist: pyext~=0.7
Requires-Dist: rouge-score~=0.1.2
Requires-Dist: scipy~=1.9.1
Requires-Dist: uncertainty-calibration~=0.1.3
Requires-Dist: scikit-learn~=1.1.2
Requires-Dist: transformers~=4.28.1
Requires-Dist: torch<3.0.0,>=1.12.1
Requires-Dist: torchvision<3.0.0,>=0.13.1
Requires-Dist: google-api-python-client~=2.64.0
Provides-Extra: proxy-server
Requires-Dist: gunicorn~=20.1.0; extra == "proxy-server"
Provides-Extra: human-evaluation
Requires-Dist: scaleapi~=2.13.0; extra == "human-evaluation"
Requires-Dist: surge-api~=1.1.0; extra == "human-evaluation"
Provides-Extra: scenarios
Requires-Dist: gdown~=4.4.0; extra == "scenarios"
Requires-Dist: sympy~=1.11.1; extra == "scenarios"
Requires-Dist: xlrd~=2.0.1; extra == "scenarios"
Provides-Extra: metrics
Requires-Dist: numba~=0.56.4; extra == "metrics"
Requires-Dist: pytrec_eval==0.5; extra == "metrics"
Requires-Dist: sacrebleu~=2.2.1; extra == "metrics"
Requires-Dist: summ-eval~=0.892; extra == "metrics"
Provides-Extra: plots
Requires-Dist: colorcet~=3.0.1; extra == "plots"
Requires-Dist: matplotlib~=3.6.0; extra == "plots"
Requires-Dist: seaborn~=0.11.0; extra == "plots"
Provides-Extra: slurm
Requires-Dist: simple-slurm~=0.2.6; extra == "slurm"
Provides-Extra: aleph-alpha
Requires-Dist: aleph-alpha-client~=2.14.0; extra == "aleph-alpha"
Requires-Dist: tokenizers~=0.13.3; extra == "aleph-alpha"
Provides-Extra: anthropic
Requires-Dist: anthropic~=0.2.5; extra == "anthropic"
Requires-Dist: websocket-client~=1.3.2; extra == "anthropic"
Provides-Extra: openai
Requires-Dist: openai~=0.27.8; extra == "openai"
Requires-Dist: tiktoken~=0.3.3; extra == "openai"
Provides-Extra: tsinghua
Requires-Dist: icetk~=0.0.4; extra == "tsinghua"
Provides-Extra: yandex
Requires-Dist: sentencepiece~=0.1.97; extra == "yandex"
Provides-Extra: models
Requires-Dist: crfm-helm[aleph-alpha]; extra == "models"
Requires-Dist: crfm-helm[anthropic]; extra == "models"
Requires-Dist: crfm-helm[openai]; extra == "models"
Requires-Dist: crfm-helm[tsinghua]; extra == "models"
Requires-Dist: crfm-helm[yandex]; extra == "models"
Provides-Extra: all
Requires-Dist: crfm-helm[server]; extra == "all"
Requires-Dist: crfm-helm[human-evaluation]; extra == "all"
Requires-Dist: crfm-helm[scenarios]; extra == "all"
Requires-Dist: crfm-helm[models]; extra == "all"
Requires-Dist: crfm-helm[metrics]; extra == "all"
Requires-Dist: crfm-helm[plots]; extra == "all"
Requires-Dist: crfm-helm[slurm]; extra == "all"
Provides-Extra: dev
Requires-Dist: pytest~=7.2.0; extra == "dev"
Requires-Dist: black~=22.10.0; extra == "dev"
Requires-Dist: mypy~=0.982; extra == "dev"
Requires-Dist: pre-commit~=2.20.0; extra == "dev"
Requires-Dist: flake8~=5.0.4; extra == "dev"

Benchmark for language models
