🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

Utilities to use the Hugging Face Hub API

This is the official implementation of "Blind Image Restoration via Fast Diffusion Inversion"

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Train transformer language models with reinforcement learning.

Offical code for the CVPR 2024 Paper: Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language

Public repo for HF blog posts

Real-time and accurate open-vocabulary end-to-end object detection

xLSTM as Generic Vision Backbone

Generative models for conditional audio generation

A generalizable application framework for segmentation, regression, and classification using PyTorch

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

YOLOv10: Real-Time End-to-End Object Detection

UniTable: Towards a Unified Table Foundation Model

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

LAVIS - A One-stop Library for Language-Vision Intelligence

PyTorch implementation of ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

Machine learning metrics for distributed, scalable PyTorch applications.

Metric depth estimation from a single image

Universal Monocular Metric Depth Estimation

Frontend components, documentation and information hosted on the Hugging Face website.

VideoMamba: State Space Model for Efficient Video Understanding

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction"

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

PyTorch code and models for V-JEPA self-supervised learning from video.

UniLM - Unified Language Model Pre-training / Pre-training for NLP and Beyond

Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.