Metadata-Version: 2.1
Name: shtec-rlhf
Version: 1.0.5
Summary: shtec-rlhf: Safe Reinforcement Learning from Human Feedback
Author: PKU-Alignment Team
License: Apache License, Version 2.0
Project-URL: Homepage, https://github.com/PKU-Alignment/shtec-rlhf
Project-URL: Repository, https://github.com/PKU-Alignment/shtec-rlhf
Project-URL: Documentation, https://shtec-rlhf.readthedocs.io
Project-URL: Bug Report, https://github.com/PKU-Alignment/shtec-rlhf
Keywords: Reinforcement Learning,Safe Reinforcement Learning,Reinforcement Learning from Human Feedback,Safe Reinforcement Learning from Human Feedback,Large Language Model,Language Model,RLHF,Safe RLHF,LLM
Classifier: Development Status :: 4 - Beta
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch (>=1.13)
Requires-Dist: transformers (>=4.37)
Requires-Dist: datasets
Requires-Dist: tokenizers (>=0.13.3)
Requires-Dist: accelerate
Requires-Dist: deepspeed
Requires-Dist: numpy
Requires-Dist: scipy
Requires-Dist: sentencepiece
Requires-Dist: wandb
Requires-Dist: tensorboard
Requires-Dist: optree
Requires-Dist: matplotlib
Requires-Dist: tqdm
Requires-Dist: rich
Provides-Extra: lint
Requires-Dist: isort (>=5.11.0) ; extra == 'lint'
Requires-Dist: black (>=23.1.0) ; extra == 'lint'
Requires-Dist: pylint[spelling] (>=2.15.0) ; extra == 'lint'
Requires-Dist: mypy (>=1.0) ; extra == 'lint'
Requires-Dist: flake8 ; extra == 'lint'
Requires-Dist: flake8-bugbear ; extra == 'lint'
Requires-Dist: flake8-comprehensions ; extra == 'lint'
Requires-Dist: flake8-docstrings ; extra == 'lint'
Requires-Dist: flake8-pyi ; extra == 'lint'
Requires-Dist: flake8-simplify ; extra == 'lint'
Requires-Dist: ruff ; extra == 'lint'
Requires-Dist: doc8 ; extra == 'lint'
Requires-Dist: pydocstyle[toml] ; extra == 'lint'
Requires-Dist: pyenchant ; extra == 'lint'
Requires-Dist: pre-commit ; extra == 'lint'

<h1 align="center">Some part of the code is fork from the Safe-RLHF project by PKU Alignment</h1>
