https://github.com/kyegomez/gpt4o

Community Open Source Implementation of GPT4o in PyTorch
https://github.com/kyegomez/gpt4o

ai gpt4o gpt5 llm ml transformers

Last synced: 29 days ago
JSON representation

Community Open Source Implementation of GPT4o in PyTorch

• Host: GitHub
• URL: https://github.com/kyegomez/gpt4o
• Owner: kyegomez
• License: mit
• Created: 2024-05-13T19:14:28.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-06-30T03:17:35.000Z (3 months ago)
• Last Synced: 2025-07-10T23:41:52.232Z (3 months ago)
• Topics: ai, gpt4o, gpt5, llm, ml, transformers
• Language: Shell
• Homepage: https://discord.gg/7VckQVxvKk
• Size: 2.16 MB
• Stars: 29
• Watchers: 3
• Forks: 5
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

README

          
[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)

# GPT4o

Community Open Source Implementation of GPT4o in PyTorch

## Install

# Architecture

- TikToken Tokenzier: We know fursure the tokenizer. [Which is here](https://github.com/openai/tiktoken)

- Model understands Images and Audio Natively. There are 2 approaches, process them natively or use encoders for each. I think here they're using encoders like whisper and vit for simplicity and brevity.

- Using DALLE3 as the output head to generate images

- Tokens to denote when to generate an image or audio

- Whisper output head for the audio outputs

# License

MIT