kreasof-ai/Homunculus-Project

Long term project about a custom AI architecture. Consist of cutting-edge technique in machine learning such as Flash-Attention, Group-Query-Attention, ZeRO-Infinity, BitNet, etc.

28
/ 100
Experimental

This project offers an experimental, custom-designed AI architecture, akin to a 'slow thinking' mechanism, that can internally iterate and 'rethink' its cognitive process. It takes various forms of input, including vision and text embeddings, and produces refined outputs like generated text or image detokenizations, guided by an internal confidence score. This is for AI researchers and machine learning engineers looking to build highly efficient and sophisticated large language models with unique internal reasoning capabilities.

No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer developing cutting-edge AI models and need an architecture that can self-correct and deepen its understanding through internal iterations.

Not ideal if you are a practitioner looking for an out-of-the-box, pre-trained model for immediate application rather than a foundational architecture for deep customization.

AI-architecture-design large-language-model-engineering deep-learning-research computational-cognition multimodal-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Python

License

AGPL-3.0

Last pushed

Oct 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/kreasof-ai/Homunculus-Project"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.