https://github.com/notshrirang/paligemma

A Vision Language Model implemented in PyTorch
https://github.com/notshrirang/paligemma

gemma gemma-2b multimodal transformers vlm

Last synced: about 1 year ago
JSON representation

A Vision Language Model implemented in PyTorch

• Host: GitHub
• URL: https://github.com/notshrirang/paligemma
• Owner: NotShrirang
• License: mit
• Created: 2024-08-11T11:32:30.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-08-25T10:13:05.000Z (almost 2 years ago)
• Last Synced: 2025-02-11T12:36:30.234Z (over 1 year ago)
• Topics: gemma, gemma-2b, multimodal, transformers, vlm
• Language: Python
• Homepage:
• Size: 19.5 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# PaliGemma

PaliGemma is a Vision Language Model (VLM) released by Google.

Base Paper - https://arxiv.org/abs/2407.07726

## Architecture:

![PaliGemma Architecture](https://github.com/user-attachments/assets/78f23d8a-d20c-43f5-b31b-e2c4438017cd)