hello-agents
Hello-Agents: a hands-on tutorial on building AI agents from scratch, covering their principles and practice.
HYSEN LABS DIRECTORY
Verified repositories, classifications and analysis from the datawhalechina organization.
Hello-Agents: a hands-on tutorial on building AI agents from scratch, covering their principles and practice.
GitHub describes it as Happy-LLM: building large language models from scratch. The repository metadata lists Jupyter Notebook as its primary language. The metadata lists the NOASSERTION license. This article stays within the project description and details documented in the GitHub repository README.
Project brief: Linux /Lora LLM / MLLM. "Open Source Large Model Eating Guide" is a tutorial for rapid fine-tuning (full parameters/Lora) and deployment of domestic and foreign open source large models (LLM)/multimodal large models (MLLM) based on Linux environment tailored for Chinese babies.
Vibe coding 101: the first course for AI-native product builders.
A tutorial on building LLM applications aimed at beginner developers. Read online: https://datawhalechina.github.io/llm-universe/
Practical LLM application development, part one: a full-stack guide to RAG technology. Read online: https://datawhalechina.github.io/all-in-rag/
An introductory tutorial on recommender systems; read online at https://datawhalechina.github.io/fun-rec/.
AI for All: The First Systematic Vibe Coding Tutorial. From Zero to Full-Stack, bring your ideas to life. Live at www.vibevibe.cn
Knowledge, code and ideas for data mining, computer vision, NLP and recommender system competitions.
Build your own embodied-intelligence robot from scratch with only basic Python knowledge; step by step build VLA, OpenVLA, SmolVLA and Pi0 models for a deep understanding of embodied AI.
Build a large language model from scratch with only basic Python knowledge; step-by-step builds of GLM4, Llama3 and RWKV6 to deeply understand how LLMs work.
Interview experience notes compiled by Datawhale members, covering machine learning, computer vision, NLP, recommendation systems and software development.
HuggingLLM, Hugging Future.
Deep Agents in Action — produced by a LangChain official ambassador, a complete guide to building production-grade AI agents from scratch using the LangChain/LangGraph ecosystem.
Covers pre-training data, tokenizer, Transformer, MoE, distributed training, scaling laws, inference and alignment. Six progressive code assignments for full-stack LLM learning.
Hello Claw! Adopt from scratch and build your first claw.
Official SGLang x Datawhale course on LLM inference (bilingual Chinese/English): understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR.
Solutions to the exercises in Statistical Learning Methods. Read online at https://datawhalechina.github.io/statistical-learning-method-solutions-manual
Proofs, worked examples, supplementary concepts and reference explanations for Introduction to the Theory of Machine Learning (the 'Treasure Box Book').
A Chinese-language translation and study guide for Andrew Ng's agent-skills-with-anthropic course series from DeepLearning.AI, with course content translation, concept summaries and example-code walkthroughs.