---
title: AntiFraud-SFT
canonical_url: "https://www.modelscope.cn/models/JimmyMa99/AntiFraud-SFT"
md_url: "https://www.modelscope.cn/models/JimmyMa99/AntiFraud-SFT.md"
repository: JimmyMa99/AntiFraud-SFT
last_updated: 2026-04-12
license: apache-2.0
model_type:
  - qwen2_audio
architectures:
  - Qwen2AudioForConditionalGeneration
parameters: 8.4B
tensor_type:
  - BF16
library_name:
  - transformer
  - safetensors
  - pytorch
frameworks:
  - Pytorch
language:
  - zh
inference_backends:
  - "deploy_task vlm/text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 139
stars: 0
tags:
  - telecom-fraud
  - audio-text
  - qwen2-audio
  - chinese
  - speech-understanding
  - supervised-fine-tuning
  - "arxiv:2503.24115"
---

# AntiFraud-SFT

> AntiFraud-SFT - JimmyMa99 在 ModelScope 开源的模型。AntiFraud-SFT is a supervised fine-tuned audio-text fraud detection model built on top of Qwen2-Audio for Chinese telecom fraud analysis.

JimmyMa99/AntiFraud-SFT 是 ModelScope 魔搭社区上的 8.4B 参数机器学习模型，采用 apache-2.0 许可，可用 deploy_task vlm/text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: JimmyMa99/AntiFraud-SFT
- **License**: apache-2.0
- **Parameters**: 8.4B
- **Inference backends**: deploy_task vlm/text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: telecom-fraud, audio-text, qwen2-audio, chinese, speech-understanding, supervised-fine-tuning, arxiv:2503.24115
- **Downloads**: 139
- **Stars**: 0
- **Last updated**: 2026-04-12

Source: https://www.modelscope.cn/models/JimmyMa99/AntiFraud-SFT

---

# AntiFraud-SFT

AntiFraud-SFT is a supervised fine-tuned audio-text fraud detection model built on top of Qwen2-Audio for Chinese telecom fraud analysis.

## Overview

This model is trained on the TeleAntiFraud-28k dataset and is designed for:

- telecom fraud detection from call audio
- scene understanding from audio-text conversational inputs
- fraud-related reasoning over Chinese phone-call content

The current release is intended as a research model checkpoint for reproduction and further study.

## Related Resources

- TeleAntiFraud dataset repository: https://github.com/JimmyMa99/TeleAntiFraud
- TeleAntiFraud dataset on Hugging Face: https://huggingface.co/datasets/JimmyMa99/TeleAntiFraud
- TeleAntiFraud dataset on ModelScope: https://www.modelscope.cn/datasets/JimmyMa99/TeleAntiFraud
- TeleAntiFraud-28k paper: https://huggingface.co/papers/2503.24115
- SAFE-QAQ code repository: https://github.com/Control-derek/SAFE-QAQ
- SAFE-QAQ paper: https://arxiv.org/abs/2601.01392

## Model Details

- Base model: `Qwen/Qwen2-Audio-7B-Instruct`
- Architecture: `Qwen2AudioForConditionalGeneration`
- Framework: PyTorch
- Weight format: `safetensors`
- License: Apache License 2.0

## Usage

This repository contains the model weights and tokenizer / processor files required for inference with `transformers`.

Example loading code:

```python
from transformers import AutoProcessor, Qwen2AudioForConditionalGeneration

model_id = "JimmyMa99/AntiFraud-SFT"

processor = AutoProcessor.from_pretrained(model_id)
model = Qwen2AudioForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
)
```

## Notes

- This release focuses on model weights for research and benchmarking.
- For evaluation scripts and LM-as-judge utilities, see the `evaluation/` directory in the TeleAntiFraud repository.
- For the end-to-end reinforcement-learning follow-up paper, see SAFE-QAQ.

## Citation

```bibtex
@inproceedings{ma2025teleantifraud,
  title={TeleAntiFraud-28k: An Audio-Text Slow-Thinking Dataset for Telecom Fraud Detection},
  author={Ma, Zhiming and Wang, Peidong and Huang, Minhua and Wang, Jinpeng and Wu, Kai and Lv, Xiangzhao and Pang, Yachun and Yang, Yin and Tang, Wenjie and Kang, Yuchen},
  booktitle={Proceedings of the 33rd ACM International Conference on Multimedia},
  pages={5853--5862},
  year={2025}
}

@article{wang2026safe,
  title={SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning},
  author={Wang, Peidong and Ma, Zhiming and Dai, Xin and Liu, Yongkang and Feng, Shi and Yang, Xiaocui and Hu, Wenxing and Wang, Zhihao and Pan, Mingjun and Yuan, Li and others},
  journal={arXiv preprint arXiv:2601.01392},
  year={2026}
}
```