PyPI page
Home page
Author:
xrsrke
License:
Apache Software License 2.0
Summary:
Implementation of Reinforcement Learning from Human Feedback (RLHF)
Latest version:
0.0.7
Required dependencies:
datasets
|
einops
|
gymnasium
|
pandas
|
pytest
|
python-dotenv
|
pytorch-lightning
|
pyyaml
|
ray
|
torch
|
torchtyping
|
tqdm
|
transformers
|
wandb
Downloads last day:
18
Downloads last week:
52
Downloads last month:
101