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

// Create text generation pipeline
const generator = await pipeline('text-generation', 'Xenova/stablelm-2-zephyr-1_6b');

// Define the prompt and list of messages
const prompt = "Tell me a funny joke."
const messages = [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": prompt },
]

// Apply chat template
const inputs = generator.tokenizer.apply_chat_template(messages, {
    tokenize: false,
    add_generation_prompt: true,
});

// Generate text
const output = await generator(inputs, { max_new_tokens: 20 });
console.log(output[0].generated_text);
// "<|system|>\nYou are a helpful assistant.\n<|user|>\nTell me a funny joke.\n<|assistant|>\nHere's a joke for you:\n\nWhy don't scientists trust atoms?\n\nBecause they make up everything!"

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).