Lordog/dive-into-llms
A free, code-oriented Chinese curriculum spans model tuning, deployment, agents, alignment, security, and multimodal systems. It is useful as a broad learning map, but remains a work in progress.
Dive into LLMs expands university course material into a free programming curriculum covering fine-tuning, deployment, model editing, watermarking, jailbreaks, RLHF, multimodal models, and agents. A **June 6, 2025** update added math reasoning, GUI agents, alignment, and steganography.
Use it as a structured map for learning the model and safety concepts behind agent systems, especially if Chinese-language slides, lab manuals, videos, and hands-on exercises fit your workflow. The newer development track is split into **beginner, intermediate, and advanced** levels.
Dive into LLMs expands university course material into a free programming curriculum covering fine-tuning, deployment, model editing, watermarking, jailbreaks, RLHF, multimodal models, and agents. A **June 6, 2025** update added math reasoning, GUI agents, alignment, and steganography. Use it as a structured map for learning the model and safety concepts behind agent systems, especially if Chinese-language slides, lab manuals, videos, and hands-on exercises fit your workflow. The newer development track is split into **beginner, intermediate, and advanced** levels. The maintainers describe the repository as an **ongoing project** based partly on contributor experience and internet material. They explicitly do not guarantee every technique is correct, so verify important claims independently.