Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

🧡 Next generation information browser.

The Power of Florence-2 with OpenVINO & FiftyOne: Real-World Applications in Image Analysis

Refine high-quality datasets and visual AI models

Triton Documentation in Chinese Simplified / Triton 中文文档

截屏 离线OCR 搜索翻译 以图搜图 贴图 录屏 万向滚动截屏 屏幕翻译 Screenshot Offline OCR Search Translate Search for picture Paste the picture on the screen Screen recorder Omnidirectional scrolling screenshot Screen translator

现代化的基于 NTQQ 的 Bot 协议端实现

Schedule-Free Optimization in PyTorch

Convert JSON annotations into YOLO format.

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

ChatGPT CLI is a versatile tool for interacting with LLM models through OpenAI and Azure, as well as models from Perplexity AI and Llama. It supports prompts and history tracking for seamless, cont…

Solve puzzles. Learn CUDA.

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Python implementation of Gerber X3/X2 standard with 2D rendering engine.

Another Mihomo GUI.

A simple dashboard for nezha.

Blackbox Protobuf is a set of tools for working with encoded Protocol Buffers (protobuf) without the matching protobuf definition.

A multimodal agent framework for solving complex tasks [EMNLP'2024]

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

A ComfyUI extension for Segment-Anything 2

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Question and Answer based on Anything.

Fine-tune SegGPT model with custom datasets

Painter & SegGPT Series: Vision Foundation Models from BAAI