Home / 🧱 AI Foundation Stack / 🏋️ Training / Fine-tuning

Enping-Hu/minimind-deep-dive

从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。

🧱 AI Foundation Stack ✓ Commercial OK ★ 95Python

Commercial license

✓ Commercial OKCC-BY-4.0

可商用,CC-BY 類需署名

Topics

deep-learningdpofine-tuningfrom-scratchgrpolarge-language-modelsllmllm-trainingminimindmoenlpppo
Ad