AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.
Petals is a project for collaboratively running llm's with high parameter counts on consumer hardware and works similar to torrents and crypto mining pools where every user of the swarm hosts and processes a small part of the language model.
It is a way of sharing ones gpu and cpu with the swarm in return for high inference speeds on big models when doing requests ourselves, and ofc the ability to run them "locally" in the first place
currently supported models LLaMA-2 70b and 70B-Chat, LLaMA-65B, Guanaco-65B and BLOOM-176B
Feature/Improvement Description
Petals is a project for collaboratively running llm's with high parameter counts on consumer hardware and works similar to torrents and crypto mining pools where every user of the swarm hosts and processes a small part of the language model. It is a way of sharing ones gpu and cpu with the swarm in return for high inference speeds on big models when doing requests ourselves, and ofc the ability to run them "locally" in the first place
currently supported models LLaMA-2 70b and 70B-Chat, LLaMA-65B, Guanaco-65B and BLOOM-176B
https://github.com/bigscience-workshop/petals https://github.com/petals-infra
Proposed Solution
add petals as ai provider
Acknowledgements