SuyogKamble/simpleVLM

building a simple VLM. Implementing LlaMA-SmolLM2 from scratch + SigLip2 Vision Model. KV-Caching is supported and implemented from scratch as well

36
/ 100
Emerging

This is a developer-focused project that helps AI researchers and deep learning engineers understand and experiment with Vision-Language Models (VLMs). It takes in images and text, processes them, and outputs textual descriptions or insights by combining visual and linguistic information. This tool is for individuals building or studying multimodal AI systems.

Use this if you are an AI researcher or deep learning engineer who needs a clear, modular, and 'from-scratch' implementation of a VLM to learn from, customize, or integrate into your own projects.

Not ideal if you are an end-user looking for a ready-to-use application or API that performs vision-language tasks without requiring deep technical understanding or development work.

AI development deep learning engineering AI research multimodal AI model building
No License No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 7 / 25
Community 15 / 25

How are scores calculated?

Stars

7

Forks

4

Language

Jupyter Notebook

License

Last pushed

Feb 19, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SuyogKamble/simpleVLM"

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