Official inference library for Mistral models

Simple Transformer in Jax

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Kolmogorov Arnold Networks

Schedule-Free Optimization in PyTorch

LLM training in simple, raw C/CUDA

Implementation of the paper 'Plug and Play Autoencoders for Conditional Text Generation'

lightweight, standalone C++ inference engine for Google's Gemma models.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Dataset of Linus Torvalds' rants classified by negativity using sentiment analysis

Sioyek is a PDF viewer with a focus on textbooks and research papers

literally just cool looking countdowns

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

A VIM-inspired filemanager for the console

Allows adding extensions from chrome web store on ungoogled-chromium. Also adds semi-automatic extension updating.

✂️ passwordless, anonymous SSH-powered pastebin with a human-friendly TUI and web UI

Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one

Inference code for Llama models

If tinygrad wasn't small enough for you...

Minimalist ML framework for Rust

Inference Llama 2 in one file of pure C

A libre lightweight streaming front-end for Android.

The open source Firebase alternative. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

Generate a PGP key from a passphrase

A feature-rich Hacker News client.

Renders papers from arXiv as responsive web pages so you don't have to squint at a PDF.

A fully compliant RISC-V computer made inside the game Terraria

You like pytorch? You like micrograd? You love tinygrad! ❤️

LLM inference in C/C++