Gabor Kukucska's Projects
Agent Zero AI framework
Wiki for AI-Net
Simple, hackable and fast implementation for training/finetuning medium-sized LLaMA-based models
Training and serving large-scale neural networks with auto parallelization.
Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.
π¬ Chatbot web app + HTTP and Websocket endpoints for LLM inference with the Petals client
My fork of an experimental open-source attempt to make GPT-4 fully autonomous.
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
Open-source software for volunteer computing and grid computing.
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Setup Davinci Resolve on Linux an Fix Issues with Importing and Exporting Media
Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models"
Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.
The worldβs fastest framework for building websites.
Prototype
Enhanced ChatGPT Clone: Features OpenAI, Assistants API, Azure, Groq, GPT-4 Vision, Mistral, Bing, Anthropic, OpenRouter, Vertex AI, Gemini, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. More features in development
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
100% Local AGI with LocalAI
Teaching LLMs memory management for unbounded context ππ¦ + Petals
The simplest, fastest repository for training/finetuning medium-sized GPTs.
old petals
Get up and running with Llama 2 and other large language models locally
User-friendly WebUI for LLMs (Formerly Ollama WebUI)
πΈ Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
ChatGPT web interface using the OpenAI API
Headless CMS with automatic JSON API. Featuring auto-HTTPS from Let's Encrypt, HTTP/2 Server Push, and flexible server framework written in Go.
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Generative Models by Stability AI