# Onnx, Error: Failed to load model because protobuf parsing failed

**URL:** <https://discuss.huggingface.co/t/onnx-error-failed-to-load-model-because-protobuf-parsing-failed/95511>\
**Category:** 🤗Transformers\
**Created:** [July 4, 2024, 12:02pm UTC](https://discuss.huggingface.co/t/onnx-error-failed-to-load-model-because-protobuf-parsing-failed/95511 "2024-07-04T12:02:04Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![mg12](https://avatars.discourse-cdn.com/v4/letter/m/7cd45c/32.png) [@mg12](https://discuss.huggingface.co/u/mg12)\
**Post date:** [July 4, 2024, 12:02pm UTC](https://discuss.huggingface.co/t/onnx-error-failed-to-load-model-because-protobuf-parsing-failed/95511/1 "2024-07-04T12:02:04Z")

</div>

Iam trying to run a model using `@xenova/transformers` but getting the following error

```auto
Error: Failed to load model because protobuf parsing failed.
    at new OnnxruntimeSessionHandler (/root/moondream/node_modules/onnxruntime-node/dist/backend.js:27:92)
    at Immediate.<anonymous> (/root/moondream/node_modules/onnxruntime-node/dist/backend.js:64:29)
    at process.processImmediate (node:internal/timers:483:21)
root@recollect-ubuntu-8gb-hel1-1:~/moondream# node index

```

this is the code

```auto
import {
  AutoProcessor,
  AutoTokenizer,
  Moondream1ForConditionalGeneration,
  RawImage,
} from "@xenova/transformers";

// Load processor, tokenizer and model
const model_id = "Xenova/moondream2";
try {
  const processor = await AutoProcessor.from_pretrained(model_id);

  const tokenizer = await AutoTokenizer.from_pretrained(model_id);

  const model = await Moondream1ForConditionalGeneration.from_pretrained(
    model_id,
    {
      dtype: {
        embed_tokens: "fp16", // or 'fp32'
        vision_encoder: "fp16", // or 'q8'
        decoder_model_merged: "q4", // or 'q4f16' or 'q8'
      },
      device: "cpu",
    }
  );

  // Prepare text inputs
  const prompt = "Describe this image.";
  const text = `<image>\n\nQuestion: ${prompt}\n\nAnswer:`;
  const text_inputs = tokenizer(text);

  // Prepare vision inputs
  const url =
    "https://huggingface.co/vikhyatk/moondream1/resolve/main/assets/demo-1.jpg";
 
  const image = await RawImage.fromURL(url);
  const vision_inputs = await processor(image);

  // Generate response
  const output = await model.generate({
    ...text_inputs,
    ...vision_inputs,
    do_sample: false,
    max_new_tokens: 64,
  });
  const decoded = tokenizer.batch_decode(output, { skip_special_tokens: false });
  console.log("answer new", decoded);
  // [
  // '<|endoftext|><image>\n\n' +
  // 'Question: Describe this image.\n\n' +
  // 'Answer: A hand is holding a white book titled "The Little Book of Deep Learning" against a backdrop of a balcony with a railing and a view of a building and trees.<|endoftext|>'
  // ]
} catch (error) {
  console.log("error", error);
}

```

System :  
node v22.4.0  
ubuntu 24.04 LTS

---

<div class="post-metadata">

**Author:** ![AhmedReda25300](https://avatars.discourse-cdn.com/v4/letter/a/ce73a5/32.png) [@AhmedReda25300](https://discuss.huggingface.co/u/AhmedReda25300)\
**Post date:** [December 21, 2024, 5:40pm UTC](https://discuss.huggingface.co/t/onnx-error-failed-to-load-model-because-protobuf-parsing-failed/95511/2 "2024-12-21T17:40:50Z")

</div>

did you find a solution?