TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.
安装
npx skills add NousResearch/hermes-agent --skill trl-fine-tuningnpx skills add NousResearch/hermes-agent --skill trl-fine-tuning -a claude-code -gnpx skills add NousResearch/hermes-agent --skill trl-fine-tuning -a codex -ggemini skills install https://github.com/NousResearch/hermes-agent.git --path optional-skills/mlops/training/trl-fine-tuninggh skill install NousResearch/hermes-agent trl-fine-tuninggit clone --depth 1 https://github.com/NousResearch/hermes-agent /tmp/NousResearch__hermes-agent
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/training/trl-fine-tuning ~/.claude/skills/trl-fine-tuning # Claude Code
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/training/trl-fine-tuning ~/.agents/skills/trl-fine-tuning # Codex, Cursor, Gemini CLI, Copilot, OpenCode