Antimatter543/karpathy-NN-lectures
My runthrough of karpathy's lectures (with notes), building NN's from scratch, simple autoregressive language models, GPT models and learnt ML techniques.
This project helps aspiring machine learning practitioners understand the foundational concepts behind neural networks by working through hands-on coding examples. It takes you from basic neural network implementation to building and debugging more complex language models. You'll put in raw text data and learn how to construct models that can generate new, similar text, gaining insight into model architecture and performance.
No commits in the last 6 months.
Use this if you want to deeply understand how neural networks, especially those for language tasks, are built from the ground up, rather than just using pre-built libraries.
Not ideal if you're looking for a quick solution to apply an existing language model or if you prefer a high-level, API-focused approach to machine learning.
Stars
10
Forks
2
Language
Jupyter Notebook
License
—
Category
Last pushed
Sep 11, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Antimatter543/karpathy-NN-lectures"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vixhal-baraiya/microgpt-c
The most atomic way to train and inference a GPT in pure, dependency-free C
milanm/AutoGrad-Engine
A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies
LeeSinLiang/microGPT
Implementation of GPT from scratch. Design to be lightweight and easy to modify.
dubzdubz/microgpt-ts
A complete GPT built from scratch in TypeScript with zero dependencies
biegehydra/NanoGptDotnet
A miniature large language model (LLM) that generates shakespeare like text written in C#....