---
license: apache-2.0
---

A tiny randomly-initialized [ViLT](https://arxiv.org/abs/2102.03334) used for unit tests in the Transformers VQA pipeline

### How to use

Here is how to use this model in PyTorch:

```python
from transformers import ViltProcessor, ViltForQuestionAnswering
import requests
from PIL import Image

# prepare image + question
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
text = "How many cats are there?"

processor = ViltProcessor.from_pretrained("hf-internal-testing/tiny-vilt-random-vqa")
model = ViltForQuestionAnswering.from_pretrained("hf-internal-testing/tiny-vilt-random-vqa")

# prepare inputs
encoding = processor(image, text, return_tensors="pt")

# forward pass
outputs = model(**encoding)
logits = outputs.logits
idx = logits.argmax(-1).item()
print("Predicted answer:", model.config.id2label[idx])
```