About
  本项目是一个从原理出发、以“白盒”为导向、围绕大模型全链路的“手搓”大模型指南，旨在帮助有传统深度学习基础的读者从底层原理出发，“纯手搓”搭建一个清晰、可用的大模型系统，包括大模型本身、RAG 框架、Agent 系统及大模型评估体系。本项目将从基础原理出发，深入剖析每一个技术点并附以完整的代码实现，以细致讲解和代码注释帮助读者独立复现大模型核心部分，并在复现中实现对大模型的深入理解与掌握。
Open Source Health
- Stars
- 5,052
- Forks
- 477
- License
- Not stated
- Last commit
- 8 months ago
Resources & Links
Related Categories
Vendor
Datawhale
For the learner，和学习者一起成长
Quick Links
Open Source
More by Datawhale
Related Products
Easy Vecdb
📚 从零开始的向量数据库原理与实践教程，在线阅读地址：https://easy-vecdb.datawhale.cc/
More from this vendor
Private Gpt
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
Top category match
PixelRAG
The end of web parsing. The beginning of scalable pixel-native search. link
Top category match
TrustRAG
TrustRAG：The RAG Framework within Reliable input,Trusted output
Top category match
RAG-Anything
"RAG-Anything: All-in-One RAG Framework"
Top category match