README.md

---
library_name: peft
license: agpl-3.0
tags:
  - opensportslib
  - sports
  - soccer
  - vqa
  - video-question-answering
  - peft
---

# OpenSportsLib VQA Model (X-VARS VideoChatGPT LoRA)

## Overview

This model is a VQA LoRA adapter produced with OpenSportsLib for soccer foul
understanding and referee-style visual question answering.

- Task: Visual Question Answering (VQA)
- Architecture: X-VARS VideoChatGPT + LoRA adapter
- Backend: `xvars_videochatgpt_lora`
- Library: OpenSportsLib
- Input: Soccer video clips plus natural-language questions
- Feature path: X-VARS-compatible CLIP features with referee priors

## Dataset

### Training Dataset

This adapter was trained on the OpenSportsLib XFoul VQA setup built on the
OSL-XFoul dataset.

- Dataset name: `OSL-XFoul`
- Domain: Soccer video understanding and officiating
- Task: Visual question answering
- Modality: Video + text
- Training samples: 16,568
- Validation samples: 2,219

## Benchmark Results

| Accuracy | Balanced Accuracy |
| ---: | ---: |
| 72.24% | 50.00% |

## Using with OpenSportsLib

For more details about OpenSportsLib:

- GitHub: https://github.com/OpenSportsLab/opensportslib
- PyPI: https://pypi.org/project/opensportslib/
- Documentation: https://opensportslab.github.io/opensportslib/

### Import the library

```python
import opensportslib
print("OpenSportsLib imported successfully")
```

### Run inference

```python
from opensportslib.apis import VQAModel

my_model = VQAModel(
    config="opensportslib/configs/vqa/xvars.yaml",
    weights="YOUR_HF_REPO_ID",
)

predictions = my_model.infer(
    test_set="/path/to/test_annotations.json",
)

single_prediction = my_model.infer(
    video_path="/path/to/video.mp4",
    question="Was this a foul? What card should be given?",
)

print(predictions)
print(single_prediction)
```

## Notes

- This repository stores a PEFT LoRA adapter, not a merged standalone base
  model.
- The adapter is intended for the OpenSportsLib X-VARS VQA path driven by
  `opensportslib/configs/vqa/xvars.yaml`.
- The original training setup used X-VARS-compatible visual features, referee
  priors, and the VideoChatGPT-style multimodal interface.

## License

- Open source license: AGPL 3.0 for research, academic, and community use.
- Commercial license: For proprietary or commercial deployment, please contact
  the project maintainers.

## Citation

```bibtex
@misc{opensportslib_xvars_vqa_xfoul_lora_2026,
  title={OpenSportsLib X-VARS VideoChatGPT LoRA for Soccer VQA},
  author={OpenSportsLab},
  year={2026},
  howpublished={https://huggingface.co/OpenSportsLab}
}
```

## Acknowledgements

- Dataset: OpenSportsLab / OSL-XFoul
- Library: https://github.com/OpenSportsLab/opensportslib
- Model pipeline: OpenSportsLib X-VARS VQA backend