LLM Tutorials大语言模型教程

Tutorials & code教程与代码

1. Neural Networks: Zero to Hero神经网络：从零到精通

   Andrej Karpathy
   Learn neural networks, backpropagation, language models and tokenizers through videos and exercises.通过视频与练习学习神经网络、反向传播、语言模型和分词器。

2. Happy-LLM

   Datawhale
   A Chinese tutorial combining theory and code to study Transformers, model building, training and applications.中文教程，结合原理与代码学习 Transformer、大模型构建、训练和应用。

3. LLMs from Scratch从零构建大语言模型

   Sebastian Raschka
   Companion code for building a GPT-style model in PyTorch, covering pretraining and fine-tuning.配套代码，用 PyTorch 逐步实现 GPT 类模型，学习预训练与微调。

4. nanoGPT

   Andrej Karpathy
   A compact GPT training codebase for source reading. The project is marked as deprecated; see its README for the author’s newer project.精简的 GPT 训练代码，可作为源码阅读材料。项目已标记为旧版，作者推荐的新项目见仓库说明。

5. CS336 · Language Modeling from ScratchCS336 · 从零构建语言模型

   Stanford · Spring 2025斯坦福大学 · 2025 年春季
   Public lectures and programming assignments on language model building, training and data processing.公开课与编程作业，覆盖语言模型构建、训练及数据处理。