Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.

🦜🔗 Build context-aware reasoning applications

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

Open-source and strong foundation image recognition models.

[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs

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…

Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios

Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts

SlimSAM: 0.1% Data Makes Segment Anything Slim

Adapting Segment Anything Model for Medical Image Segmentation

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

A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。

Bring portraits to life!

A library for efficient similarity search and clustering of dense vectors.

A guide for hacking unity games

GUI Application to work with engine assets, asset bundles, and serialized files

Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVION and PaddlePaddle. （将PaddleOCR模型做了转换，采用ONNXRuntime推理，速度很快）

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Open standard for machine learning interoperability

Automated upstream mirror for libbpf stand-alone build.

The official Meta Llama 3 GitHub site

High-level tracing language for Linux

pbrt 中文整合翻译 基于物理的渲染：从理论到实现 Physically Based Rendering: From Theory To Implementation

BCC - Tools for BPF-based Linux IO analysis, networking, monitoring, and more

Official repository for the BPF Performance Tools book

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)