robert-mcdermott/LLM-Image-Classification

Image Classification Testing with LLMs

38
/ 100
Emerging

This project explores using advanced AI models (multimodal LLMs) to categorize images based on their content, moving beyond traditional methods that just analyze visual features. It takes an image as input and outputs a classification (e.g., 'cat', 'dog', 'number 7'). This would be used by data scientists or machine learning practitioners looking to leverage open-source, vision-enabled language models for image sorting and content identification.

No commits in the last 6 months.

Use this if you are a data scientist exploring the capabilities of open-source multimodal large language models for image classification and want to understand their current out-of-the-box performance.

Not ideal if you need highly accurate, production-ready image classification for specific categories, as this model shows limitations in accuracy for certain types of images without fine-tuning.

image-classification computer-vision machine-learning-research multimodal-ai data-science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

72

Forks

9

Language

Python

License

Apache-2.0

Last pushed

Jan 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/robert-mcdermott/LLM-Image-Classification"

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