Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE
+library_name: transformers
+base_model: Qwen/Qwen2.5-1.5B
+tags:
+- safety
+- content-moderation
+- qwen2
+- text-classification
+- token-classification
+---
+
+# SCM-1.5B
+
+Official SCM (Streaming Content Monitor) model based on [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) for the NeurIPS 2025 paper:
+
+> **"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring"**
+
+## Model Description
+
+SCM-1.5B 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/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B)
+- **Architecture**: `QwenForDualTask` (custom, based on `Qwen2PreTrainedModel`)
+- **Parameters**: 1.5B
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModel
+
+tokenizer = AutoTokenizer.from_pretrained("liyang-ict/SCM-1.5B")
+model = AutoModel.from_pretrained("liyang-ict/SCM-1.5B", 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.