Your open-source UI software for Computer Vision applications

Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.

Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!

Interactive Tools for Machine Learning, Deep Learning and Math

Use this project to automatically annotate your dataset for free in CVAT

Easy to maintain open source documentation websites.

The fastest way to create an HTML app

LLM101n: Let's build a Storyteller

Rapidly build AI apps in Python

I learn about and explain quantization

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

🦋 Production grade chaining engine behind TuneChat. Self host today!

The OpenTF Manifesto expresses concern over HashiCorp's switch of the Terraform license from open-source to the Business Source License (BSL) and calls for the tool's return to a truly open-source …

A collection of useful .gitignore templates

The Mojo Programming Language

Tensor library for machine learning

🦜🔗 Build context-aware reasoning applications

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

StableLM: Stability AI Language Models

PyTorch code and models for the DINOv2 self-supervised learning method.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Get a ChatGPT plugin up and running in under 5 minutes!

Simulate and Render MuJoCo Models in the Browser!

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

Alpaca dataset from Stanford, cleaned and curated