Gabor Kukucska's Projects
Wiki for AI-Net
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"
The worldβs fastest framework for building websites.
Prototype
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
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.
Generative Models by Stability AI
π₯ Health monitor for a Petals swarm
Text Generation Web UI for Large Language Models. Supports transformers, GPTQ, AWQ, llama.cpp (GGUF), Llama models.
Ai written Trade bot
Robust Speech Recognition via Large-Scale Weak Supervision