整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

Natural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Dependency Parsing, Document Classification

Repository for the second edition of 'Data Science in Education Using R' by Emily A. Bovee, Ryan A. Estrellado, Joshua M. Rosenberg, and Isabella C. Velásquez