OralGPT-OPG-7B-Instruct

Finetuning the Qwen2.5-VL-7B using MMOral-Report and MMOral-VQA data for panoramic X-ray Analysis.

📄 Paper: https://arxiv.org/pdf/2509.09254

📦 Model configuration

model_name_or_path: OralGPT/OralGPT-OPG-7B-Instruct
template: qwen2_vl
infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
trust_remote_code: true

🚀 Dtart inference API

API_PORT=8001 llamafactory-cli api LLaMA-Factory/examples/inference/qwen2_5vl.yaml

Citation

@article{hao2025towards,
  title={Towards better dental ai: A multimodal benchmark and instruction dataset for panoramic x-ray analysis},
  author={Hao, Jing and Fan, Yuxuan and Sun, Yanpeng and Guo, Kaixin and Lin, Lizhuo and Yang, Jinrong and Ai, Qi Yong H and Wong, Lun M and Tang, Hao and Hung, Kuo Feng},
  journal={arXiv preprint arXiv:2509.09254},
  year={2025}
}