High-quality datasets, tools, and concepts for LLM fine-tuning.

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

A pytorch quantization backend for optimum

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Make drawing and labeling bounding boxes easy as cake

Gradio UI for a Cog API

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

We write your reusable computer vision tools. 💜

Strong and Open Vision Language Assistant for Mobile Devices

the AI-native open-source embedding database

Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

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

A guidance language for controlling large language models.

Alpaca dataset from Stanford, cleaned and curated

A scikit-learn compatible neural network library that wraps PyTorch

It's a cooler way to store simple linear models.

The pytest framework makes it easy to write small tests, yet scales to support complex functional testing

Data Analysis Baseline Library

Chrome/Firefox extension to replace instances of "OpenAI" with "ClosedAI" all over the web

Terraform enables you to safely and predictably create, change, and improve infrastructure. It is a source-available tool that codifies APIs into declarative configuration files that can be shared …

this is where we share notebooks/projects used in your youtube channel

Get Started MLEM project

Vision Transformer Cookbook with Tensorflow