PyPI page
Home page
Author:
Zera Lyngkhoi
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:
0.1.28
Required dependencies:
accelerate
|
bert-score
|
bitsandbytes
|
click
|
curatorkit
|
cut-cross-entropy
|
datasets
|
diffusers
|
evaluate
|
filelock
|
heapdict
|
hf-transfer
|
huggingface-hub
|
immutables
|
lm-eval
|
matplotlib
|
mlx
|
mlx-lm
|
mlx-vlm
|
msgspec
|
nest-asyncio
|
nltk
|
numpy
|
packaging
|
pandas
|
peft
|
pillow
|
protobuf
|
psutil
|
pydantic
|
pyicu
|
pypdf
|
python-docx
|
pyyaml
|
regex
|
requests
|
rich
|
rouge-score
|
sacrebleu
|
safetensors
|
scikit-learn
|
scipy
|
sentence-transformers
|
sentencepiece
|
sqlglot
|
tensorboard
|
tokenizers
|
torch
|
torchao
|
torchvision
|
tqdm
|
transformers
|
triton
|
triton-windows
|
trl
|
typer
|
typing-extensions
|
tyro
|
wandb
|
wheel
|
xformers
Optional dependencies:
black
|
curatorkit
|
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:
16
Downloads last week:
48
Downloads last month:
828
7-day smoothing