Wheelodex » Projects » llamagym

llamagym

View on PyPI — Reverse Dependencies (0)

0.1.1 llamagym-0.1.1-py3-none-any.whl

Wheel Details

Project: llamagym
Version: 0.1.1
Filename: llamagym-0.1.1-py3-none-any.whl
Download: [link]
Size: 5734
MD5: a47312d15e969c981f0655176711536e
SHA256: 24cf73effc11cc9d1fd5bef8d5d59816982c39ef8147a95b203f04094f04f046
Uploaded: 2024-03-10 09:06:52 +0000

dist-info

METADATA · WHEEL · RECORD

METADATA

Metadata-Version: 2.1
Name: llamagym
Version: 0.1.1
Summary: Fine-tune LLM agents with online reinforcement learning
Author: Rohan Pandey
License: MIT
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.9,<4.0
Requires-Dist: accelerate (<0.22.0,>=0.21.0)
Requires-Dist: bitsandbytes (<0.41.0,>=0.40.0)
Requires-Dist: gymnasium (<0.30.0,>=0.29.1)
Requires-Dist: peft (<0.8.0,>=0.7.1)
Requires-Dist: scipy (<2.0.0,>=1.12.0)
Requires-Dist: textworld (<2.0.0,>=1.6.1)
Requires-Dist: torch (<3.0.0,>=2.1.2)
Requires-Dist: transformers (<5.0.0,>=4.36.2)
Requires-Dist: trl (<0.8.0,>=0.7.9)
Requires-Dist: wandb (<0.17.0,>=0.16.4)
Description-Content-Type: text/markdown
[Description omitted; length: 4429 characters]

WHEEL

Wheel-Version: 1.0
Generator: poetry-core 1.9.0
Root-Is-Purelib: true
Tag: py3-none-any

RECORD

Path Digest Size
llamagym/__init__.py sha256=P-vxd39oVQ_2ueMwbkp4BVr4Ooi5z5a2noPdl9pohSk 24
llamagym/agent.py sha256=VQ0ckb6bTK0gXEPIn4-KKtNyyrgjR2bkSVhZX0GzUSU 6029
llamagym-0.1.1.dist-info/LICENSE sha256=VNdNwBYtYVWIVntif16VLyYv-LyjSAeQSD0ppi4C8ko 1069
llamagym-0.1.1.dist-info/METADATA sha256=GwzArcYjiC-eABuEZk4krRBeHSJCByklH4cVumDzox8 5373
llamagym-0.1.1.dist-info/WHEEL sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg 88
llamagym-0.1.1.dist-info/RECORD — —