karpathy / cryptos
Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes
☆1,692Updated 3 years ago
Alternatives and similar repositories for cryptos:
Users that are interested in cryptos are comparing it to the libraries listed below
- Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world …☆627Updated last year
- An autoregressive character-level language model for making more things☆2,937Updated 9 months ago
- A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API☆11,453Updated 7 months ago
- Some ipython notebooks implementing AI algorithms☆1,311Updated 5 months ago
- Notebooks and various random fun☆1,090Updated last year
- The n-gram Language Model☆1,402Updated 7 months ago
- The Autograd Engine☆581Updated 6 months ago
- From the Tensor to Stable Diffusion, a rough outline for a 1 week course.☆1,055Updated 2 months ago
- Video+code lecture on building nanoGPT from scratch☆3,989Updated 7 months ago
- NanoGPT (124M) in 3 minutes☆2,403Updated this week
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆9,502Updated 8 months ago
- If tinygrad wasn't small enough for you...☆699Updated last year
- A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training☆21,600Updated 7 months ago
- Neural Networks: Zero to Hero☆13,419Updated 7 months ago
- The Tensor (or Array)☆427Updated 7 months ago
- The full minitorch student suite.☆2,029Updated 7 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 …☆1,248Updated last year
- The comma.ai Calibration Challenge!☆973Updated last year
- 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.☆120Updated 2 years ago
- The Multilayer Perceptron Language Model☆543Updated 7 months ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,252Updated 3 months ago
- ☆3,865Updated last year
- Letting computers listen to you and really care☆369Updated 2 years ago
- UNet diffusion model in pure CUDA☆600Updated 8 months ago
- Solve puzzles. Improve your pytorch.☆3,483Updated 8 months ago
- nanoGPT style version of Llama 3.1☆1,341Updated 7 months ago
- From the Transistor to the Web Browser, a rough outline for a 12 week course☆5,456Updated 3 years ago
- LLM training in simple, raw C/CUDA☆26,079Updated 5 months ago
- "build a modern computer from first principles"☆14Updated 5 years ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆5,892Updated last week