Factual package intelligence from PyPI

llm-rewards 0.0.1 package intelligence

Lean, modular reward functions for RL training with LLMs

pip install llm-rewards

Current version
0.0.1
Python requirement
>=3.8
License
MIT License
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
22.8 KiB
Release history
1 releases with files
Median release cadence
Not enough dated releases

llm-rewards dependencies

PyPI declares 20 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. torch >=2.0.0
  2. transformers >=4.36.0
  3. tqdm >=4.65.0
  4. numpy >=1.24.0
  5. pandas >=2.0.0
  6. accelerate >=0.24.0
  7. bitsandbytes >=0.41.0
  8. scipy >=1.11.0
  9. datasets >=2.14.0
  10. sentencepiece >=0.1.99
  11. protobuf >=4.24.0
  12. einops >=0.6.1
  13. typing-extensions >=4.5.0

The compact report shows 18 of 20 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

llm-rewards publishes 1 wheel and 1 source archive for version 0.0.1. Wheel platform tags: any.

Declared Python classifiers: 3.10, 3.8, 3.9.

Release activity and sources

PyPI lists 1 release with files. The first dated release is ; 1 release falls within the 365 days preceding the latest dated release. The current release files were uploaded on .