Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.
安装
npx skills add huggingface/skills --skill trl-trainingnpx skills add huggingface/skills --skill trl-training -a claude-code -gnpx skills add huggingface/skills --skill trl-training -a codex -ggemini skills install https://github.com/huggingface/skills.git --path skills/trl-traininggh skill install huggingface/skills trl-traininggit clone --depth 1 https://github.com/huggingface/skills /tmp/huggingface__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/huggingface__skills/skills/trl-training ~/.claude/skills/trl-training # Claude Code
cp -R /tmp/huggingface__skills/skills/trl-training ~/.agents/skills/trl-training # Codex, Cursor, Gemini CLI, Copilot, OpenCode