granite-4.0-micro-ONNX

Transformers.js

[!IMPORTANT]
Note: This model requires Transformers.js v4.0.0 and above!

Example: Basic example

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

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/granite-4.0-micro-ONNX",
  { dtype: "q4f16", device: "webgpu" },
);

// Define the list of messages
const messages = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "What is the capital of France?" },
];

// Generate a response
const output = await generator(messages, {
    max_new_tokens: 512,
    do_sample: false,
    streamer: new TextStreamer(generator.tokenizer, { skip_prompt: true, skip_special_tokens: true }),
});
console.log(output[0].generated_text.at(-1).content);
// The capital of France is Paris.