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 modeling training methods, plus GGUF conversion for local deployment.
Install
npx skills add huggingface/skills --skill huggingface-llm-trainernpx skills add huggingface/skills --skill huggingface-llm-trainer -a claude-code -gnpx skills add huggingface/skills --skill huggingface-llm-trainer -a codex -ggemini skills install https://github.com/huggingface/skills.git --path skills/huggingface-llm-trainergh skill install huggingface/skills huggingface-llm-trainergit clone --depth 1 https://github.com/huggingface/skills /tmp/huggingface__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/huggingface__skills/skills/huggingface-llm-trainer ~/.claude/skills/huggingface-llm-trainer # Claude Code
cp -R /tmp/huggingface__skills/skills/huggingface-llm-trainer ~/.agents/skills/huggingface-llm-trainer # Codex, Cursor, Gemini CLI, Copilot, OpenCode