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

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/MobileLLM-125M",
  { dtype: "fp32" },
);

// Define the list of messages
const text = "Q: What is the capital of France?\nA: Paris\nQ: What is the capital of England?\nA:";

// Generate a response
const output = await generator(text, { max_new_tokens: 30 });
console.log(output[0].generated_text);

Example output

Q: What is the capital of France?
A: Paris
Q: What is the capital of England?
A: London
Q: What is the capital of Scotland?
A: Edinburgh
Q: What is the capital of Wales?
A: Cardiff

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).