Update README.md

README.md

@@ -4,27 +4,39 @@ datasets:
 - Mireu-Lab/NSL-KDD
 metrics:
 - accuracy
-base_model:
-- Qwen/Qwen2.5-0.5B
-pipeline_tag: text-generation
+- f1
+base_model: Qwen/Qwen2.5-0.5B
+pipeline_tag: text-classification
 tags:
-- intrusion detection
+- intrusion-detection
+- cybersecurity
+- llm
+- qwen
+- tabular-reasoning
 ---
-PCF_ID: A Novel Prompt Cast Framework for Intrusion Detection
 
+# PCF_ID: A Novel Prompt Cast Framework for Intrusion Detection
 
-[![Hugging Face Model](https://img.shields.io/badge/Hugging%20Face-Model-blue)](https://huggingface.co/your_model_name_here)
+[![Hugging Face Model](https://img.shields.io/badge/Hugging%20Face-Model-blue)](https://huggingface.co/PHZane/PCF_ID-0.5B)
 [![Python 3.8+](https://img.shields.io/badge/Python-3.8%2B-blue)](https://www.python.org/)
-[![License](https://img.shields.io/badge/License-Apache%202.0-green.svg)](https://opensource.org/licenses/Apache-2.0)
+[![License](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
 
-📌 模型概述
+## 📌 Model Overview
 
-PCF_ID-0.5B ，通过 PCF-ID 框架针对结构化入侵检测数据进行了微调，实现了从原始 LLMs 到安全领域应用的重大跃迁：
+**PCF_ID-0.5B** is a fine-tuned version of **Qwen2.5-0.5B**, adapted for network intrusion detection using the **Prompt Cast Framework (PCF-ID)**. By transforming structured tabular records into semantically rich **Question–Reasoning–Answer (Q-R-A)** prompts, PCF_ID enables large language models to effectively reason over cybersecurity data.
 
-准确率：高达 94%以上
+Key results on the **NSL-KDD** benchmark:
+- **Accuracy**:  >94%
+- **Precision**: >0.97
+- **Recall**:    >0.95
+- **F1 Score**:  >0.96
 
-F1 分数：达到 0.94以上
+PCF_ID-0.5B significantly outperforms:
+- Raw LLMs (e.g., vanilla Qwen2.5-0.5B),
+- Traditional machine learning models (e.g., Random Forest, SVM),
+- Advanced graph neural networks (GNNs).
 
-在标准入侵检测NSL-KDD基准上显著优于大模型，传统机器学习方法和先进的图神经网络。
+## 💻 Code & Reproduction
 
-代码提供在：https://github.com/Zaneph1/PCF_ID
+The full framework, preprocessing pipeline, and evaluation scripts are available at:  
+🔗 [https://github.com/Zaneph1/PCF_ID](https://github.com/Zaneph1/PCF_ID)