Stars
Python implementation and interpretation of "Elliptic Fourier Features of a Closed Contour" with enhanced start point and rotation normalization methods.
Access a database of word frequencies, in various natural languages.
Chai-1, SOTA model for biomolecular structure prediction
Easy OpenAPI specs and Swagger UI for your Flask API
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images
Convolutional Neural Networks to predict the aesthetic and technical quality of images.
Open Source Text Embedding Models with OpenAI Compatible API
Main repository for tuk lab equipment allocation system
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"
ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, th…
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，支持GraphRAG，无须安装任何第三方agent库。
闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
Universal LLM Deployment Engine with ML Compilation
✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows
SHARK Studio -- Web UI for SHARK+IREE High Performance Machine Learning Distribution
🦄️ 🎃 👻 Clash Premium 规则集(RULE-SET)，兼容 ClashX Pro、Clash for Windows 等基于 Clash Premium 内核的客户端。
Making large AI models cheaper, faster and more accessible
使用GPT-3.5 API创建的ChatGPT聊天页面，支持云部署，多用户使用，多对话管理，公式显示，流式动态显示，windows和linux均可极简部署，网页版 html python flask
Port of OpenAI's Whisper model in C/C++
Python implementation of A. Levin D. Lischinski and Y. Weiss. A Closed Form Solution to Natural Image Matting. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2006, New York