Work through university lab exercises on large language models
Made by Tongxin Yuan
View profile on GitHub (opens in a new tab)A free hands-on tutorial series on large language models, grown out of two courses at Shanghai Jiao Tong University on frontier language technology and AI security.
It is written as programming practice rather than theory: notebooks you run, with topics that have expanded over time to include mathematical reasoning, agents that drive graphical interfaces, model alignment and steganography. A companion series developed with Huawei’s Ascend community covers the full development cycle on Chinese hardware, with slides, lab manuals and video at beginner, intermediate and advanced levels.
Can I use this?
You'll need Python, a notebook environment and some GPU access · Setup needed
Worth knowing The material is in Chinese, so it is only usable if you read Chinese or are willing to work through a translation. The authors state plainly that the content comes from personal experience and internet sources and that they do not guarantee it is all correct. The companion Huawei series targets Ascend hardware specifically, which is not what most readers will have. The repository publishes no licence. BuildTube has not run or verified this software.
Why it's here
Not trending this week
Last seen on the GitHub trending list on 20 September 2026. It stays on BuildTube so you can still find it.
- 55,767 people have starred it on GitHub.
Numbers checked on 6 October 2026; not refreshed since.
Behind it
See the code on GitHubBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?