Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
Install
npx skills add davila7/claude-code-templates --skill fine-tuning-with-trlnpx skills add davila7/claude-code-templates --skill fine-tuning-with-trl -a claude-code -gnpx skills add davila7/claude-code-templates --skill fine-tuning-with-trl -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/post-training-trl-fine-tuninggh skill install davila7/claude-code-templates fine-tuning-with-trlgit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/post-training-trl-fine-tuning ~/.claude/skills/fine-tuning-with-trl # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/post-training-trl-fine-tuning ~/.agents/skills/fine-tuning-with-trl # Codex, Cursor, Gemini CLI, Copilot, OpenCode