PipelineLLM 是一个系统性的大语言模型（LLM）后训练学习项目，涵盖从监督微调（SFT）到偏好优化（DPO）、强化学习（RLHF/PPO/GRPO）再到持续学习（Continual Learning)的完整技术栈。
rankextractplus extracts and structures ranked info from text, organizing data for easier comparison and analysis.
📝 Extract and structure ranked information from unstructured text using RankExtractPlus, a Python package powered by large language models.
Add a description, image, and links to the llm-processing topic page so that developers can more easily learn about it.
To associate your repository with the llm-processing topic, visit your repo's landing page and select "manage topics."