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.

查看源碼 machine-learning

maintainer

huggingface

更新於 2/16/2026

星標

17998

分支

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.

安裝

$ install --globalskills.sh

使用

安裝後，您可以通過在終端運行以下命令來使用此技能：

skills use trl-training