PyPI page
Home page
Author:
Rajarshi, Gurpreet, Danush
License:
Apache 2.0
Summary:
Train transformer language models with reinforcement learning.
Latest version:
0.0.15
Required dependencies:
accelerate
|
datasets
|
deepspeed
|
nltk
|
numpy
|
peft
|
scipy
|
stanza
|
torch
|
transformers
|
tyro
|
wandb
Optional dependencies:
bitsandbytes
|
deepspeed
|
diffusers
|
ghapi
|
huggingface-hub
|
llm-blender
|
openai
|
openrlbenchmark
|
parameterized
|
peft
|
pillow
|
pytest
|
pytest-cov
|
pytest-xdist
|
requests
|
scikit-learn
|
wandb
Downloads last day:
1
Downloads last week:
11
Downloads last month:
54