PyPI page
Home page
Author:
Leandro von Werra
Summary:
Train transformer language models with reinforcement learning.
Latest version:
0.20.0.dev0
Required dependencies:
accelerate
|
datasets
|
transformers
Optional dependencies:
bitsandbytes
|
deepspeed
|
diffusers
|
fastapi
|
joblib
|
liger-kernel
|
llm-blender
|
openai
|
parameterized
|
peft
|
pillow
|
pydantic
|
pytest
|
pytest-cov
|
pytest-rerunfailures
|
pytest-xdist
|
requests
|
scikit-learn
|
uvicorn
|
vllm
Downloads last day:
0
Downloads last week:
3
Downloads last month:
9
7-day smoothing