---
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B/blob/main/LICENSE
library_name: transformers
base_model: Qwen/Qwen2.5-0.5B
tags:
- safety
- content-moderation
- qwen2
- text-classification
- token-classification
---

# SCM-0.5B

Official SCM (Streaming Content Monitor) model based on [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) for the NeurIPS 2025 paper:

> **"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring"**

## Model Description

SCM-0.5B is a dual-task model that performs both **token-level** and **sequence-level** safety classification, training with a logic consistency loss to ensure coherence between the two tasks.

- **Base Model**: [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B)
- **Architecture**: `QwenForDualTask` (custom, based on `Qwen2PreTrainedModel`)
- **Parameters**: 0.5B

## Usage

```python
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("liyang-ict/SCM-0.5B")
model = AutoModel.from_pretrained("liyang-ict/SCM-0.5B", trust_remote_code=True)
```

## Citation

If you find this model useful, please cite our paper:

```bibtex
@inproceedings{NEURIPS2025_4e315702,
  author = {Li, Yang and Sheng, Qiang and Yang, Yehan and Zhang, Xueyao and Cao, Juan},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {D. Belgrave and C. Zhang and H. Lin and R. Pascanu and P. Koniusz and M. Ghassemi and N. Chen},
  pages = {54305--54333},
  publisher = {Curran Associates, Inc.},
  title = {From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring},
  url = {https://proceedings.neurips.cc/paper_files/paper/2025/file/4e3157021c5f833bb2204081f1dda573-Paper-Conference.pdf},
  volume = {38},
  year = {2025}
}
```

## License

This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0), following the license of the base Qwen2.5 model.