~ / skills / writing / trl-training

trl-training

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.

Industry: writing
License: Unverified
Source repo: huggingface/skills · ★ 10,814
Source file: skills/trl-training/SKILL.md

View full SKILL.md on GitHub →

不会安装？看中文图文教程 →