A large collection of ready-made LLM apps: agents, RAG systems and skills for coding agents. Every template can be run and taken apart piece by piece.
All repositories
Awesome lists & learningkarpathy
micrograd
A tiny autograd engine with a small neural net on top and a PyTorch-like API. Very little code, yet it shows exactly how backpropagation works.
Who it is for
For people who want to see backpropagation in a few lines of code.
How to start
- Install the package:
pip install micrograd - Run the README example with
Valueand callg.backward() - Train a small neural net following the Training a neural net section
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+391Sep 6 — Oct 5
Author's description
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
More in «Awesome lists & learning»
A free 21-lesson Microsoft course that goes from generative AI basics and prompting to working applications. Each lesson ships with code.
Code for Sebastian Raschka's book: you build a GPT-like model in PyTorch step by step, then pretrain and finetune it. The best way to see how an LLM works inside.
An animation engine Grant Sanderson uses to make 3Blue1Brown videos, including the well-known neural network ones. It is not an AI library but a tool for explaining math and ML visually.
A 12-week course on classic machine learning: 26 lessons and 52 quizzes. The foundation that makes modern models easier to understand.
A three-part LLM roadmap: fundamentals, the LLM Scientist (building models) and the LLM Engineer (building apps). Topics come with Colab notebooks.