awacke1's picture
Update README.md
fdae7e3 verified
|
raw
history blame
1.57 kB
---
title: 🧠Omni GPT 4o Text Audio Image Video
emoji: 🐠🔬🧠
colorFrom: gray
colorTo: blue
sdk: streamlit
sdk_version: 1.34.0
app_file: app.py
pinned: true
license: mit
---
GPT-4o Documentation: https://cookbook.openai.com/examples/gpt4o/introduction_to_gpt4o
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
This experimental multi agent mixture of expert system uses a variety of techniques and models to create different combinatorial AI solutions.
Models Used:
Mistral-7B-Instruct
Llama2-7B
Mixtral-8x7B-Instruct
Google Gemma-7B
OpenAI Whisper Small En
OpenAI GPT-4o, Whisper-1
ArXiV Embeddings
The techniques below which are not ML models but AI include:
Speech Synthesis using browser technology
Memory for semantic facts, and episodic emotional and event time series memories
Web integration using the q= standard for search linking allowing comparison of tech giant AI implementations:
Bing then Bing copilot with click 2
Google which does an AI search now
Twitter, the new home for technology discoveries, AI Output and Grok
Wikipedia for fact checking
YouTube
File and metadata integration combining text, audio, image, and video
This app also merges common theories in cognitive AI, AI with python libraries (e.g. NLTK, SKLearn).
The intent is to demonstrate SOTA AI/ML and combinations of Function-Input-Output for interoperability and knowledge management.
This space also serves as an experimental test bed for new technologies mixing it in with old for comparison and integration.
--Aaron