Welcome to trlX’s documentation!

trlX is a library made for training large language models using reinforcement learning. It currently supports training using PPO or ILQL for models up to 20B using Accelerate.

Installation

pip install "trlx"

Contents:

• How To build the documentation
• Data Elements
• Configs
• Pipelines and Rollout Store
• RL Trainers

Indices and tables

• Index

• Module Index

• Search Page