PyPI page
Home page
Author:
Zibo He, Le Su
License:
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTI...
Summary:
An easy-to-use, fast toolkit to scale up RL post-training on a single node.
Latest version:
0.9.0
Required dependencies:
addict
|
av
|
click
|
datasets
|
fastapi
|
flash-linear-attention
|
huggingface-hub
|
librosa
|
math-verify
|
mlx
|
mlx-lm
|
mlx-vlm
|
modelscope
|
numpy
|
openai
|
prompt-toolkit
|
pydantic
|
rich
|
safetensors
|
soundfile
|
tensorboard
|
tensorboardx
|
torch
|
torchvision
|
tqdm
|
transformers
|
uvicorn
Optional dependencies:
flash-attn
Downloads last day:
3
Downloads last week:
68
Downloads last month:
67
7-day smoothing