Overview

From scratch implementation of PaliGemma

Technical Details

• Framework: PyTorch
• Dataset: Flickr
• Category: Computer Vision

Implementation Details

Paligemma architecture in Pytorch

I implemented the Paligemma using Pytorch on the flickr8000 dataset.

PaliGemma: A versatile 3B VLM for transfer

Datasets

flickr 8000: Link

Frameworks:

Pytorch

Source Code

📁 GitHub Repository: PaliGemma

View the complete implementation, training scripts, and documentation on GitHub.