PyPI page
Home page
Author:
None
License:
MIT
Summary:
Guided Group Relative Policy Optimization (GRPO) training for MLX on Apple Silicon
Latest version:
2.1.1
Required dependencies:
mlx
|
mlx-lm
|
numpy
|
pyyaml
|
tqdm
|
transformers
Optional dependencies:
black
|
isort
|
pytest
|
scikit-learn
|
wandb
Downloads last day:
0
Downloads last week:
23
Downloads last month:
42