karpathy / cryptosLinks
Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes
☆1,737Updated 3 years ago
Alternatives and similar repositories for cryptos
Users that are interested in cryptos are comparing it to the libraries listed below
Sorting:
- An autoregressive character-level language model for making more things☆3,109Updated last year
- If tinygrad wasn't small enough for you...☆716Updated last year
- Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world …☆637Updated last year
- ☆3,991Updated last year
- Some ipython notebooks implementing AI algorithms☆1,341Updated 3 weeks ago
- A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API☆12,040Updated 9 months ago
- The n-gram Language Model☆1,421Updated 10 months ago
- Notebooks and various random fun☆1,095Updated 2 years ago
- Tutorials on tinygrad☆381Updated 3 weeks ago
- NanoGPT (124M) in 3 minutes☆2,610Updated last week
- The Autograd Engine☆609Updated 8 months ago
- nanoGPT style version of Llama 3.1☆1,372Updated 9 months ago
- 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.☆126Updated 2 years ago
- The Multilayer Perceptron Language Model☆549Updated 9 months ago
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆9,671Updated 11 months ago
- Repository for the book☆1,809Updated last year
- The comma.ai Calibration Challenge!☆971Updated last year
- Solve puzzles. Improve your pytorch.☆3,579Updated 10 months ago
- arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors …☆1,297Updated last year
- The Tensor (or Array)☆433Updated 9 months ago
- What would you do with 1000 H100s...☆1,050Updated last year
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,518Updated this week
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,265Updated 5 months ago
- Tile primitives for speedy kernels☆2,420Updated this week
- Llama from scratch, or How to implement a paper without crying☆567Updated last year
- Language model alignment-focused deep learning curriculum☆1,397Updated 9 months ago
- An unnecessarily tiny implementation of GPT-2 in NumPy.☆3,362Updated 2 years ago
- A modern model graph visualizer and debugger☆1,212Updated last week
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,784Updated last month
- UNet diffusion model in pure CUDA☆606Updated 11 months ago