Hugging Face Interactive published

Text Generation

Generate text continuations with a small GPT-2 family model running in the browser.

Transformers.js Demo

Run ML models directly in your browser

idle

Select Model

Distilled version of GPT-2, faster and lighter

Input Text

Output

Results will appear here after running inference

Model Information

This demo uses Xenova/distilgpt2

View on Hugging Face

How This Works

This demo uses Transformers.js to run machine learning models directly in your browser using WebAssembly. No data is sent to any server—all inference happens locally on your device.