mentriaai/Qwen3.5-0.8B-quotes-ONNX

import { AutoProcessor, AutoModelForImageTextToText, TextStreamer } from '@huggingface/transformers';

const MODEL_ID = 'mentriaai/Qwen3.5-0.8B-quotes-ONNX';

const processor = await AutoProcessor.from_pretrained(MODEL_ID);
const model = await AutoModelForImageTextToText.from_pretrained(MODEL_ID, {
  dtype: { embed_tokens: 'q4', vision_encoder: 'fp16', decoder_model_merged: 'q4' },
  device: 'webgpu',
});

const messages = [
  { role: 'system', content: 'You are a poetic thinker. Write one short, original motivational quote (1-2 sentences). Do not attribute it to anyone. No preamble, no quotation marks — just the quote itself.' },
  { role: 'user', content: [{ type: 'text', text: 'Give me a motivational quote.' }] },
];

const textContent = processor.apply_chat_template(messages, {
  tokenize: false,
  add_generation_prompt: true,
});

const inputs = await processor(textContent, null, { padding: true, truncation: true });

const streamer = new TextStreamer(processor.tokenizer, {
  skip_prompt: true,
  skip_special_tokens: true,
  callback_function(token) {
    process.stdout.write(token);
  },
});

await model.generate({
  ...inputs,
  max_new_tokens: 128,
  do_sample: true,
  temperature: 0.9,
  top_p: 0.95,
  streamer,
});

onnx/
  decoder_model_merged_q4.onnx       (813 KB graph + 452 MB weights)
  embed_tokens_q4.onnx               (857 B graph + 155 MB weights)
  vision_encoder_fp16.onnx           (183 KB graph + 195 MB weights)