🦜🔗 The platform for reliable agents.

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

Ultralytics YOLO 🚀

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

The official Meta Llama 3 GitHub site

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

State-of-the-art 2D and 3D Face Analysis Project

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

DeepSeek Coder: Let the Code Write Itself

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Retrieval and Retrieval-augmented LLMs

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Implementation of Nougat Neural Optical Understanding for Academic Documents

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

A PyTorch implementation of EfficientNet

Utilities intended for use with Llama models.

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

PyTorch deep learning projects made easy.

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

Accompanying code for Paperspace tutorial series "How to Implement YOLO v3 Object Detector from Scratch"

Convolutional neural network model for video classification trained on the Kinetics dataset.

Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training