joyehuang/minimind-notes
🚀 [从零构建 LLM] 极简大模型训练原理与实践指南。包含 Transformer, Pretraining, SFT 核心代码与对照实验。 | A minimal, principle-first guide to understanding and building LLMs from scratch.
This project offers a hands-on guide to deeply understand how large language models (LLMs) like GPT or Llama are trained. It uses simplified code and comparative experiments to show not just 'how to do it,' but 'why it works.' It's for AI/ML engineers, students, and researchers who want to master the core principles behind LLM development.
Use this if you are preparing for LLM-related job interviews, or if you want to move beyond just using AI frameworks to truly understanding the underlying mechanics of modern LLMs.
Not ideal if you are completely new to deep learning with PyTorch, only want to quickly deploy models without understanding their internal workings, or need production-ready code with best practices.
Stars
67
Forks
8
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/joyehuang/minimind-notes"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AI-Hypercomputer/maxtext
A simple, performant and scalable Jax LLM!
rasbt/reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step
mindspore-lab/mindnlp
MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless...
mosaicml/llm-foundry
LLM training code for Databricks foundation models
rickiepark/llm-from-scratch
<밑바닥부터 만들면서 공부하는 LLM>(길벗, 2025)의 코드 저장소