karpathy / microgradLinks
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
☆13,335Updated 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☆3,355Updated last year
- You like pytorch? You like micrograd? You love tinygrad! ❤️☆30,376Updated this week
- ☆4,272Updated last year
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,064Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆47,749Updated 10 months ago
- Video+code lecture on building nanoGPT from scratch☆4,469Updated last year
- A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training☆22,797Updated last year
- Neural Networks: Zero to Hero☆18,068Updated last year
- LLM101n: Let's build a Storyteller☆35,120Updated last year
- An unnecessarily tiny implementation of GPT-2 in NumPy.☆3,421Updated 2 years ago
- Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes☆1,822Updated 4 years ago
- Some ipython notebooks implementing AI algorithms☆1,386Updated 5 months ago
- Inference Llama 2 in one file of pure C☆18,872Updated last year
- The n-gram Language Model☆1,461Updated last year
- Explanation to key concepts in ML☆8,105Updated 3 months ago
- Solve puzzles. Improve your pytorch.☆3,754Updated last year
- llama3 implementation one matrix multiplication at a time☆15,180Updated last year
- Flax is a neural network library for JAX that is designed for flexibility.☆6,865Updated last week
- From the Transistor to the Web Browser, a rough outline for a 12 week course☆6,353Updated 4 years ago
- If tinygrad wasn't small enough for you...☆743Updated last year
- The full minitorch student suite.☆2,207Updated last year
- From the Tensor to Stable Diffusion, a rough outline for a 1 week course.☆1,072Updated 3 weeks ago
- Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more☆33,791Updated this week
- Notebooks and various random fun☆1,109Updated 2 years ago
- A concise but complete full-attention transformer with a set of promising experimental features from various papers☆5,633Updated last week
- Development repository for the Triton language and compiler☆17,289Updated last week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,079Updated 3 months ago
- tiktoken is a fast BPE tokeniser for use with OpenAI's models.☆16,330Updated 3 weeks ago
- LLM training in simple, raw C/CUDA☆27,923Updated 4 months ago
- A multi-backend implementation of the Keras API, with support for TensorFlow, JAX, and PyTorch.☆1,263Updated 4 months ago