Hugging Face JavaScript

Run ML models locally with Transformers.js or via the Inference API. Supports text generation, embeddings, image classification, speech recognition, and more.

Transformers.js (Local Inference)

Run models directly in browser or Node.js using ONNX Runtime.

npm install @huggingface/transformers

Text Generation

import { pipeline } from '@huggingface/transformers';

const generator = await pipeline('text-generation', 'Xenova/gpt2');