trl-training

Name: trl-training
Author: huggingface

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

소스 보기 machine-learning

maintainer

huggingface

업데이트됨 2/16/2026

스타

17998

포크

2632

quick start

Installation and usage

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

설치

$ install --globalskills.sh

사용법

설치 후 터미널에서 다음 명령을 실행하여 이 스킬을 사용할 수 있습니다:

skills use trl-training