PyPI page
Home page
Author:
None
License:
MIT
Summary:
AlignTune: Multi-backend alignment and fine-tuning library. Features TRL and Unsloth backends with complete RL coverage (DPO, PPO, GRPO, BOLT), 27+ reward functions, production-ready evaluation system, and unified configuration interface for LLM alignment.
Latest version:
0.1.7
Required dependencies:
accelerate
|
bitsandbytes
|
click
|
datasets
|
evaluate
|
huggingface-hub
|
lm-eval
|
matplotlib
|
nltk
|
numpy
|
nvidia-ml-py
|
nvitop
|
pandas
|
peft
|
psutil
|
pyyaml
|
rich
|
rouge-score
|
sacrebleu
|
scikit-learn
|
seaborn
|
tensorboard
|
tqdm
|
transformers
|
trl
|
typer
|
unsloth
|
unsloth_zoo
|
wandb
Optional dependencies:
black
|
flake8
|
hypothesis
|
isort
|
mypy
|
myst-parser
|
pre-commit
|
pytest
|
pytest-cov
|
pytest-mock
|
pytest-timeout
|
pytest-xdist
|
sphinx
|
sphinx-autodoc-typehints
|
sphinx-rtd-theme
Downloads last day:
6
Downloads last week:
86
Downloads last month:
242