3,358 dependents
| Package | Description | Downloads/month |
|---|---|---|
| SGLang is a high-performance serving framework for large language models and mul... | 287.7M | |
| The largest collection of PyTorch image encoders / backbones. Including train, e... | 13.2M | |
| Ultralytics YOLO 🚀 | 10.6M | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 9.4M | |
| An open source implementation of CLIP. | 3.1M | |
| Ready-to-use OCR with 80+ supported languages and all popular writing scripts in... | 2.7M | |
| This package contains the AI models used by the Docling PDF conversion package | 2.4M | |
| Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt... | 1.9M | |
| Give your project support for a variety of PyTorch model architectures, includin... | 1.8M | |
| WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarizatio... | 1.1M | |
| The fastai deep learning library | 994K | |
| Fast and Accurate ML in 3 Lines of Code | 859K | |
| Semantic segmentation models with 500+ pretrained convolutional and transformer-... | 704K | |
| gavin's function library | 535K | |
| High-fidelity performance metrics for generative models in PyTorch | 528K | |
| PyTorch - FID calculation with proper image resizing and quantization steps [CVP... | 518K | |
| A Data Streaming Library for Efficient Neural Network Training | 515K | |
| 🔎 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS,... | 487K | |
| CUGA is an open-source generalist agent harness for the enterprise, supporting c... | 450K | |
| MatterSim: A deep learning atomistic model across elements, temperatures and pre... | 418K | |
| Auxillary models for controlnet | 354K | |
| This is a background removing tool powered by InSPyReNet (ACCV 2022) | 348K | |
| Packaged version of ultralytics/yolov5 + many extra features | 332K | |
| Implements extra model architectures for spandrel | 327K | |
| Package for image deduplication | 319K | |
| docTR (Document Text Recognition) - a seamless, high-performing & accessible lib... | 287K | |
| A python library for self-supervised learning on images. | 250K | |
| Speed up model training by fixing data loading. | 246K | |
| TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial ... | 232K | |
| 228K | ||
| [ICLR 2026] RF-DETR is a real-time object detection and segmentation model archi... | 222K | |
| 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning | 204K | |
| Face analysis tools for modern research, equipped with state-of-the-art Face Par... | 193K | |
| Convert ONNX models to PyTorch. | 181K | |
| Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResne... | 179K | |
| The code used to train and run inference with the ColVision models, e.g. ColPali... | 164K | |
| Convert ONNX models to PyTorch. | 156K | |
| spotriver - Sequential Parameter Optimization Interface to River | 136K | |
| A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs). | 132K | |
| A fast and simple implementation of learning algorithms for robotics. | 131K | |
| A toolset for compressing, deploying and serving LLM | 123K | |
| BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and p... | 122K | |
| Audiocraft is a library for audio processing and generation with deep learning. ... | 122K | |
| The new inference engine for Computer Vision models | 117K | |
| Implementation of Vision Transformer, a simple way to achieve SOTA in vision cla... | 109K | |
| Retinaface get 80.99% in widerface hard val using mobilenet0.25. | 108K | |
| 108K | ||
| ⚠️DirectML is in maintenance mode ⚠️ DirectML is a high-performance, hardware-ac... | 108K | |
| 100K | ||
| Computer vision models on PyTorch | 96K |
