{"version":"1.0","workflow_uuid":"7989ba1c-3daf-4fd1-bf5b-f1b16b6ca990","workflow_title":"TRL — Post-Training LLMs with RLHF & DPO","install_contract":{"version":"1.0","installReady":false,"title":"TRL — Post-Training LLMs with RLHF & DPO","summary":"TRL is a Hugging Face library for post-training foundation models. 17.9K+ GitHub stars. SFT, GRPO, DPO, reward modeling. Scales from single GPU to multi-node. Apache 2.0.","assetType":"Scripts","pageUrl":"https://tokrepo.com/en/workflows/trl-post-training-llms-rlhf-dpo-7989ba1c","sourceUrl":"https://github.com/huggingface","intendedFor":[],"firstActions":[],"agentFirstSteps":[],"targetPaths":[],"verification":[],"startingPoints":[],"example":"","successOutcome":"","boundaries":[],"askUserIf":["the current workspace stack cannot be matched to a safe upstream template","the target path is not the project root, or an existing file should be merged instead of overwritten"]}}