karpathy / microgradLinks
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
☆14,143Updated last year
Alternatives and similar repositories for micrograd
Users that are interested in micrograd are comparing it to the libraries listed below
Sorting:
- An autoregressive character-level language model for making more things☆3,523Updated last year
- Neural Networks: Zero to Hero☆19,391Updated last year
- You like pytorch? You like micrograd? You love tinygrad! ❤️☆30,930Updated this week
- ☆4,419Updated last year
- Inference Llama 2 in one file of pure C☆19,046Updated last year
- A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training☆23,198Updated last year
- Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes☆1,855Updated 4 years ago
- LLM training in simple, raw C/CUDA☆28,459Updated 6 months ago
- Video+code lecture on building nanoGPT from scratch☆4,620Updated last year
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,225Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆51,230Updated last month
- NanoGPT (124M) in 3 minutes☆3,974Updated this week
- Solve puzzles. Improve your pytorch.☆3,851Updated last year
- Some ipython notebooks implementing AI algorithms☆1,394Updated 7 months ago
- Tensor library for machine learning☆13,743Updated last week
- MLX: An array framework for Apple silicon☆23,176Updated this week
- An unnecessarily tiny implementation of GPT-2 in NumPy.☆3,434Updated 2 years ago
- Development repository for the Triton language and compiler☆17,920Updated this week
- Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world …☆701Updated last year
- Machine Learning Engineering Open Book☆16,071Updated last week
- Explanation to key concepts in ML☆8,245Updated 5 months ago
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,840Updated last year
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆16,818Updated 2 months ago
- If tinygrad wasn't small enough for you...☆759Updated last year
- The full minitorch student suite.☆2,260Updated last year
- Language model alignment-focused deep learning curriculum☆1,505Updated last year
- Ongoing research training transformer models at scale☆14,686Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,169Updated 4 months ago
- llama3 implementation one matrix multiplication at a time☆15,203Updated last year
- Unsupervised text tokenizer for Neural Network-based text generation.☆11,525Updated last week