Factual package intelligence from PyPI

thinkbooster 0.1.1 package intelligence

ThinkBooster: a unified framework for test-time compute scaling of LLM reasoning

pip install thinkbooster

Current version
0.1.1
Python requirement
>=3.10
License
MIT
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
664.4 KiB
Release history
2 releases with files
Median release cadence
0 days

thinkbooster dependencies

PyPI declares 34 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. torch >=1.9.0
  2. transformers >=4.56.0
  3. datasets >=2.14.0
  4. numpy >=1.23.5
  5. tqdm >=4.64.0
  6. parse >=1.19.0
  7. hydra-core >=1.2.0
  8. omegaconf >=2.2.0
  9. python-dotenv >=0.19.0
  10. lm-polygraph >=0.6.0
  11. pylatexenc >=2.10
  12. sympy >=1.12
  13. regex >=2023.0.0
  14. plotly >=5.0.0
  15. word2number >=1.1
  16. wandb >=0.15.0
  17. evalplus >=0.3.1
  18. vllm <0.13.0,>=0.12.0

The compact report shows 25 of 34 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

thinkbooster publishes 1 wheel and 1 source archive for version 0.1.1. Wheel platform tags: any.

Declared Python classifiers: 3.11.

Release activity and sources

PyPI lists 2 releases with files. The first dated release is ; 2 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .