onnx-community/HY-MT1.5-1.8B-ONNX

Usage (Transformers.js)

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

You can then use the model to translate text as follows:

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

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/HY-MT1.5-1.8B-ONNX",
  { dtype: "q4", device: "webgpu" },
);

// Define the list of messages
const target_lang = "Chinese";
const prompt = "It’s on the house.";
const messages = [
  { role: "user", content: `Translate the following segment into ${target_lang}, without additional explanation.\n\n${prompt}` },
];

// 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);