Fast Library for Approximate Nearest Neighbors

AI Toolkit for Healthcare Imaging

Official implementation of LLaVa-Rad, a small multimodal model for chest X-ray findings generation.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

A flexible package for multimodal-deep-learning to combine tabular data with text and images using Wide and Deep models in Pytorch

Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Tutorials for creating and using ONNX models

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Official implementation of MedCLIP-SAM (MICCAI 2024)

Effortless data labeling with AI support from Segment Anything and other awesome models.

yolov8 model with SAM meta

Auto Segmentation label generation with SAM (Segment Anything) + Grounding DINO

[ NeurIPS MAR 2024 ] Official Codebase for "Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding"

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)

A guidance language for controlling large language models.

An open-source implementaion for fine-tuning Phi3-Vision and Phi3.5-Vision by Microsoft.

This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small langua…

Strong and Open Vision Language Assistant for Mobile Devices

A family of lightweight multimodal models.

Everything about the SmolLM and SmolVLM family of models

[MICCAI 2024, top 11%] Official Pytorch implementation of Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

🚴 Call stack profiler for Python. Shows you why your code is slow!