Datawhale China team is an open-sourced large-scale pre-trained language model tutorial project, which aims to provide systematic knowledge and technical support for people who are interested in large language models, so as to gain an in-depth understanding and master the principles, applications and related technologies of large models.
The project will be based on Stanford University's large-scale language model course and Li Hongyi's generative AI course, combined with the supplementation and improvement from open source contributors, as well as the timely update of cutting-edge large model knowledge, to provide readers with more comprehensive and in-depth theoretical knowledge and practical methods. Through the systematic explanation of model construction, training, evaluation and improvement, as well as the actual practice of code.
内容地址：https://datawhalechina.github.io/so-large-lm
开源地址：https://github.com/datawhalechina/so-large-lm 
