PyPI page
Home page
Author:
None
Summary:
The OpenPipe Agent Reinforcement Training (ART) library
Latest version:
0.5.18
Required dependencies:
causal-conv1d
|
deep-ep
|
litellm
|
mamba-ssm
|
ml-dtypes
|
nest-asyncio
|
nvidia-cudnn-frontend
|
nvidia-resiliency-ext
|
openai
|
polars
|
setproctitle
|
tblib
|
typer
|
weave
Optional dependencies:
accelerate
|
apex
|
awscli
|
bitsandbytes
|
datrie
|
duckdb
|
fastapi
|
gql
|
hf-xet
|
huggingface-hub
|
langchain-core
|
langchain-openai
|
langgraph
|
matplotlib
|
megatron-bridge
|
megatron-core
|
nbclient
|
nbmake
|
numpy
|
nvidia-ml-py
|
peft
|
pillow
|
pyarrow
|
pybind11
|
pydantic
|
pytest
|
quack-kernels
|
seaborn
|
setuptools
|
tinker
|
tinker-cookbook
|
torch
|
torchao
|
transformer-engine
|
transformer-engine-cu12
|
transformer-engine-torch
|
transformers
|
trl
|
unsloth
|
unsloth-zoo
|
uvicorn
|
wandb
Downloads last day:
757
Downloads last week:
3,473
Downloads last month:
17,150