llama2

🤖 Automate your Instagram with Riona AI, a local AI solution that enhances privacy and streamlines social media management.

A simple, performant, and scalable Jax LLM!

Run a Llama2 inference engine in 1189 bytes of x86 assembly that boots directly from disk beneath any operating system.

Automate your personal knowledge base in Obsidian using Claude. Feed raw content and let the LLM organize, link, and synthesize your notes.

Translate human intent into Claude-ready prompts for cleaner, faster LLM coding tasks

🤖 Enhance customer support with an AI chat platform that delivers intelligent, context-aware responses through a seamless full-stack solution.

🔍 Capture browser traffic and automatically generate clean Python API clients with this efficient CLI tool. No more manual reverse engineering.

🌟 Create a fast, modern blog with the Firefly Astro theme, featuring responsive design, customizable colors, and support for animations.

Integrate Higgs v3 TTS into ComfyUI for multilingual speech synthesis, zero-shot voice cloning, emotional control, and dialogue generation.

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

Orchestrate fault-tolerant, ultra-scalable GPU training for trillion-parameter LLMs with ZeRO-3 and PyTorch FSDP.

Proxy the GitHub Copilot API to support custom integrations through a reliable, rewritten interface.

Provide lightweight, zero-dependency C++17 single-header libraries to integrate large language models into native applications efficiently.

🤖 Build and manage a production-grade agent infrastructure stack using TypeScript, Node.js, and Terraform for seamless deployment and robust performance.

🧠 Generate dynamic narratives with LMD, a framework for episodic memory that evolves, feels, and tells stories through creative language grounding.

🤖 Automate chat replies on Android without root using just 10 lines of code. Ideal for testing with Autojs or Hamibot.

📍 Store text locations in vector databases for QA tasks, enhancing citation accuracy and retrieval precision in RAG systems.

🤖 Build a responsive chatbot with Streamlit and LangChain that offers real-time AI interactions using Google's Gemini models.

🐙 Explore the inner workings of large language models with hands-on Python and PyTorch code. Master LLM architecture, training, and mechanisms for AI systems.

lcpp is a dart implementation of llama.cpp used by the mobile artificial intelligence distribution (maid)