Factual package intelligence from PyPI

simplet5-trl 0.2.0 package intelligence

simpleT5-TRL is built on top of HuggingFace Transformers and TRL that lets you quickly train encoder-decoder models (T5, BART, T5Gemma, etc.) with full finetuning, LoRA, QLoRA, DPO, SimPO, and RFT support.

pip install simplet5-trl

Current version
0.2.0
Python requirement
>=3.9
License
MIT
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
46.5 KiB
Release history
3 releases with files
Median release cadence
1 days

simplet5-trl dependencies

PyPI declares 16 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. numpy ==1.26.4
  2. pandas ==1.3.5
  3. scipy ==1.15.0
  4. sentencepiece ==0.2.1
  5. torch ==2.9.1
  6. transformers ==5.0.0rc1
  7. trl ==0.26.2
  8. peft ==0.18.0
  9. bitsandbytes ==0.49.0
  10. accelerate ==1.12.0
  11. datasets >=2.14.0
  12. rouge-score >=0.1.2
  13. torchaudio ==2.9.1
  14. torchvision ==0.24.1
  15. tf-keras ==2.20.1
  16. pillow ==12.0.0

Compatibility and release files

simplet5-trl publishes 1 wheel and 1 source archive for version 0.2.0. Wheel platform tags: any.

Declared Python classifiers: 3.10, 3.11, 3.12, 3.9.

Release activity and sources

PyPI lists 3 releases with files. The first dated release is ; 3 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .