🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
- nlp
- natural-language-processing
- pytorch
- pytorch-transformers
Repository Index
56,638 visible repositories in the index
1–24 of 460 · Most stars
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
- stable-diffusion
- pytorch
- ai
- python
LLM inference in C/C++
- ggml
real time face swap and one-click video deepfake with only a single image
- ai-face
- deepfake
- video-deepfake
- deepfake-webcam
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
scikit-learn: machine learning in Python
Deep Learning for humans
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
- ultralytics
- yolov8
- yolo
- deep-learning
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
- yolov5
- object-detection
- pytorch
- onnx
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.
Port of OpenAI's Whisper model in C/C++
We write your reusable computer vision tools. 💜
- computer-vision
- image-processing
- python
- yolo
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
AirLLM 2.8T LLM inference with single 4GB GPU
- chinese-nlp
- finetune
- generative-ai
- instruct-gpt
Making large AI models cheaper, faster and more accessible
- deep-learning
- hpc
- large-scale
- data-parallelism
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
- abliteration
- llm
- transformer
- censorship-resistance
A generative speech model for daily dialogue.
- agent
- text-to-speech
- chat
- chatgpt
SGLang is a high-performance serving framework for large language models and multimodal models.
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
- pytorch
- gan
- deep-learning
- super-resolution
Cross-platform, customizable ML solutions for live and streaming media.
- mediapipe
- c-plus-plus
- computer-vision
- deep-learning
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
- pytorch
- resnet
- pretrained-models
- pretrained-weights
Official Code for DragGAN (SIGGRAPH 2023)
- artificial-intelligence
- generative-adversarial-network
- generative-models
- image-manipulation