cff-version: 1.2.0
title: 'TRL: Transformers Reinforcement Learning'
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Leandro
    family-names: von Werra
  - given-names: Younes
    family-names: Belkada
  - given-names: Lewis
    family-names: Tunstall
  - given-names: Edward
    family-names: Beeching
  - given-names: Tristan
    family-names: Thrush
  - given-names: Nathan
    family-names: Lambert
  - given-names: Shengyi
    family-names: Huang
  - given-names: Kashif
    family-names: Rasul
  - given-names: Quentin
    family-names: Gallouédec
repository-code: 'https://github.com/huggingface/trl'
abstract: >-
  TRL (Transformers Reinforcement Learning) is an
  open-source toolkit for aligning transformer models via
  post-training. It provides practical, scalable
  implementations of SFT, reward modeling, DPO, and GRPO
  within the Hugging Face ecosystem.
keywords:
  - transformers
  - reinforcement learning
  - preference optimization
  - language model alignment
  - post-training
license: Apache-2.0
version: '1.2'
date-released: '2020-03-27'