AI
Florence-2 is a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks.
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Home voice assistant using RaspberryPi
Face Recognition using RPI5 Hailo8L AI Accelerator KIT
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
2025 - This is my deployment environment for real world AI robot policies, and a place to create training data for reinforcement learning and imitation learning.
The best OSS video generation models, created by Genmo
Scalable and memory-optimized training of diffusion models
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
High-performance In-browser LLM Inference Engine
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
100+ Fine-tuning Tutorial Notebooks on Google Colab, Kaggle and more.
A framework for serving and evaluating LLM routers - save LLM costs without compromising quality
Integrate cutting-edge LLM technology quickly and easily into your apps
This repository includes examples of using Microsoft Semantic Kernel with local LLMS via Ollama
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
🤗 smolagents: a barebones library for agents that think in code.
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
Force DeepSeek r1 models to think for as long as you wish