Your power level is hidden. Claim to reveal.
Add your token data, projects, and blog posts.5 hackers already claimed.
Request removalThis profile was created from public information.
karpathy
Andrej
0Tokens
340Commits
0Props
51.9MBCode Out
10Essays
54Projects
About me
I like to train Deep Neural Nets on large datasets.
Tech Stack
// null
Proficiency Levels
HTML
[]
Jupyter Notebook
[]
Python
[]
Cuda
[]
JavaScript
[]
C
[]
Lua
[]
Makefile
[]
C++
[]
CSS
[]
Shell
[]
Rust
[]
MATLAB
[]
Perl
[]
M
[]
Batchfile
[]
Pinned
The simplest, fastest repository for training/finetuning medium-sized GPTs.
nanoGPTGitHub
The best ChatGPT that $100 can buy.
nanochatGitHub
LLM training in simple, raw C/CUDA
llm.cGitHub
Inference Llama 2 in one file of pure C
llama2.cGitHub
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
microgradGitHub
All projects