Factual package intelligence from PyPI

bitnet-v3 1.0.1 package intelligence

BitNet v3: Ultra-Low Quality Loss 1-bit LLMs Through Multi-Stage Progressive Quantization and Adaptive Hadamard Transform

pip install bitnet-v3

Current version
1.0.1
Python requirement
>=3.8
License
MIT
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
115.1 KiB
Release history
2 releases with files
Median release cadence
1 days

bitnet-v3 dependencies

PyPI declares 33 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. torch >=2.0.0
  2. torchvision >=0.15.0
  3. numpy >=1.21.0
  4. scipy >=1.7.0
  5. einops >=0.6.0
  6. accelerate >=0.20.0
  7. transformers >=4.30.0
  8. datasets >=2.0.0
  9. tokenizers >=0.13.0
  10. tqdm >=4.60.0
  11. pyyaml >=6.0
  12. omegaconf >=2.3.0
  13. wandb >=0.15.0
  14. tensorboard >=2.13.0
  15. bitsandbytes >=0.41.0
  16. safetensors >=0.3.0

The compact report shows 25 of 33 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

bitnet-v3 publishes 1 wheel and 1 source archive for version 1.0.1. Wheel platform tags: any.

Declared Python classifiers: 3.10, 3.11, 3.8, 3.9.

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 .