0hq/WebGPT

Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.

44
/ 100
Emerging

This project helps developers and educators explore and implement large language models directly within web browsers. It takes a pre-trained GPT model and its weights, and runs it entirely client-side, showing how a transformer model can generate text without server interaction. The primary user is a web developer, a machine learning engineer, or an educator interested in WebGPU capabilities.

3,784 stars. No commits in the last 6 months.

Use this if you are a web developer or educator wanting to understand and demonstrate how large language models can run directly in a web browser using WebGPU.

Not ideal if you are looking for a production-ready, highly optimized, or easy-to-use library to integrate GPT models into a live application without deep technical understanding.

web-development machine-learning-engineering browser-technology educational-resource GPU-computing-web
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

3,784

Forks

222

Language

JavaScript

License

Last pushed

Jan 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/0hq/WebGPT"

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