M

multimodal

ein — a single vector for many things. Embedding server around EmbeddingGemma 2: many text/image/audio chunks in one POST /embed → exactly ONE weighted-centroid vector, shared 768-dim space. Node.js + TypeScript, Python sidecar, CUDA auto-detect.

Ultralytics fork of Apple MobileCLIP for fast image-text inference, training, evaluation, and an iOS demo.

GitHub: https://github.com/ultralytics/mobileclip

https://docs.ultralytics.com

OpenAI CLIP for zero-shot image-text classification and embeddings with ResNet and Vision Transformer models.

GitHub: https://github.com/ultralytics/CLIP

https://www.ultralytics.com

Single-header C++17: send images (file or URL) plus a prompt to OpenAI or Anthropic vision models. Part of llm-cpp.

QuantumLingua is an open-source, high-speed AI translation platform that uses Model Compression and Parallelization (MCP) to deliver fast, accurate, and adaptive multilingual translations. It supports text, audio, images, and video, enables real-time collaboration, prioritizes privacy and security, and empowers communities, researchers, and enterprises with futuristic, personalized, and multimodal translation tools. https://roxanneardary.com/quantumlingua/

The Anal-Queen of AI Browser Automation 🏴‍☠️ A beautifully fucked-up Skynet-powered browser automation script that harnesses neural brainfuck and machine learning chaos to give zero shits about anything while somehow still working perfectly.

API FastAPI permettant d’identifier des espèces de pingouins à partir de données tabulaires optionnelles et/ou d’une image.

L’API renvoie une liste d’espèces probables avec leurs probabilités et inclut :

Classification Machine Learning (RF, KNN, LR) Fusion multimodale (tabulaire + image) Journalisation des requêtes/réponses (SQLite) Interface web pour consulter les logs Interface web pour tester les prédictions Notebooks pour exploration et entraînement

Projet réalisé dans le cadre de la formation Développeur en Intelligence Artificielle (Simplon).

PDF + Image + Table → LLaVA / Qwen2-VL

Terminal Chat Completion client for Google's Gemini AI models written in Go

MF-3DPnP is a non-learning-based pipeline for robust geometric pose estimation using monocular vision, sparse or dense depth, and optional inertial measurements (IMU). It is designed as a strong baseline for comparing pure geometric approaches to modern learning-based methods, with a particular focus on aerial and robotics datasets (such as EuRoC and TUM-VI).

Aplicação de chat multimodal que utiliza I.A

A multimodal knowledge graph about monuments in The Netherlands