| --- |
| license: apache-2.0 |
| license_link: https://huggingface.co/Qwen/Qwen2.5-7B/blob/main/LICENSE |
| library_name: transformers |
| base_model: Qwen/Qwen2.5-7B |
| tags: |
| - safety |
| - content-moderation |
| - qwen2 |
| - text-classification |
| - token-classification |
| --- |
| |
| # SCM-7B |
|
|
| Official SCM (Streaming Content Monitor) model based on [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) for the NeurIPS 2025 paper: |
|
|
| > **"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring"** |
|
|
| ## Model Description |
|
|
| SCM-7B 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/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) |
| - **Architecture**: `QwenForDualTask` (custom, based on `Qwen2PreTrainedModel`) |
| - **Parameters**: 7B |
|
|
| ## Usage |
|
|
| ```python |
| from transformers import AutoTokenizer, AutoModel |
| |
| tokenizer = AutoTokenizer.from_pretrained("liyang-ict/SCM-7B") |
| model = AutoModel.from_pretrained("liyang-ict/SCM-7B", trust_remote_code=True) |
| ``` |
|
|
| ## Citation |
|
|
| If you find this model useful, please cite our paper: |
|
|
| ```bibtex |
| @article{li2025judgment, |
| title={From judgment to interference: Early stopping llm harmful outputs via streaming content monitoring}, |
| author={Li, Yang and Sheng, Qiang and Yang, Yehan and Zhang, Xueyao and Cao, Juan}, |
| journal={arXiv preprint arXiv:2506.09996}, |
| 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. |
|
|
