~ / skills / writing / huggingface-llm-trainer

huggingface-llm-trainer

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward…

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

View full SKILL.md on GitHub →

不会安装？看中文图文教程 →