This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment.
Install
npx skills add huggingface/skills --skill hugging-face-model-trainernpx skills add huggingface/skills --skill hugging-face-model-trainer -a claude-code -gnpx skills add huggingface/skills --skill hugging-face-model-trainer -a codex -ggemini skills install https://github.com/huggingface/skills.git --path skills/hugging-face-model-trainergh skill install huggingface/skills hugging-face-model-trainergit clone --depth 1 https://github.com/huggingface/skills /tmp/huggingface__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/huggingface__skills/skills/hugging-face-model-trainer ~/.claude/skills/hugging-face-model-trainer # Claude Code
cp -R /tmp/huggingface__skills/skills/hugging-face-model-trainer ~/.agents/skills/hugging-face-model-trainer # Codex, Cursor, Gemini CLI, Copilot, OpenCode