SmolDocling via ONNX Inference Outputting Gibberish?

### Bug
Since I've struggled to get SmolDocling working with Transformers in a Windows-based Python environment, I've switched to running it in a Docker container using Docling's own image (ghcr.io/docling-project/docling-serve-cu124). I'm using the code provided on the [Hugging Face model card](https://huggingface.co/ds4sd/SmolDocling-256M-preview) to run it via ONNX. When I input two example documents mentioned by Docling ([GazetteFrance.jpg](https://upload.wikimedia.org/wikipedia/commons/7/76/GazettedeFrance.jpg) & [page_with_table.png](https://ibm.biz/docling-page-with-table)), both documents yield gibberish like the following:

```
A
```

Any suggestions on how to fix this? The model I'm running was obtained by running the command docling-tools models download smolvlm. Is it possible this has downloaded an incompatible version?

### Docling version
Docling version: 2.34.0
Docling Core version: 2.32.0
Docling IBM Models version: 3.4.3
Docling Parse version: 4.0.1
Python: cpython-312 (3.12.10)
Platform: Linux-5.15.167.4-microsoft-standard-WSL2-x86_64-with-glibc2.34

### Python version
Python 3.12.10