0hq/WebGPT
Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.
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.
Stars
3,784
Forks
222
Language
JavaScript
License
—
Category
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.
Compare
Higher-rated alternatives
tabularis-ai/be_great
A novel approach for synthesizing tabular data using pretrained large language models
EleutherAI/gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron...
shibing624/textgen
TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet...
ai-forever/ru-gpts
Russian GPT3 models.
AdityaNG/kan-gpt
The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold...