diff --git a/README.en.md b/README.en.md
new file mode 100644
index 0000000000000000000000000000000000000000..f30cfc5d10adec01e8b5b479cd86c993bc2d4b53
--- /dev/null
+++ b/README.en.md
@@ -0,0 +1,52 @@
+
+
+# Detect-AI
+
+Detect-AI is a project designed to detect and classify AI-generated text. It combines deep learning and traditional statistical methods, utilizing the BERT model and statistical features for text analysis.
+
+## Features
+
+- Uses BERT to extract semantic features from text.
+- Extracts statistical features and integrates LSTM for deep feature fusion.
+- Supports comparative analysis between traditional machine learning models and deep learning models.
+- Provides model saving and loading capabilities for convenient training and deployment.
+
+## Project Structure
+
+- `src/dev/ClassifyModel.py`: Implements model definition and feature fusion logic.
+- `src/dev/FeatExtractor.py`: Provides statistical feature extraction functionality.
+- `src/dev/comparison.py`: Supports comparison between traditional machine learning models and deep learning models.
+- `src/dev/data.py`: Defines datasets and data loading logic.
+- `src/dev/load_save.py`: Provides utility functions for saving and loading models.
+- `src/dev/kfcValidate.py`: Implements K-fold cross-validation.
+- `src/dev/train.py`: Core code for the training process.
+- `src/dev/evaluation.py`: Model evaluation logic.
+- `src/dev/configs.py`: Global configuration information.
+- `training/data/train/alldata.jsonl`: Dataset file.
+
+## Usage
+
+1. Install dependencies:
+   ```bash
+   pip install torch transformers scikit-learn
+   ```
+
+2. Prepare data:
+   - Data should be in JSONL format and stored in the `training/data/train/` directory.
+
+3. Train the model:
+   - Launch the training process using `train.py`. Specific parameters can be adjusted via configuration files.
+
+4. Model evaluation:
+   - Use `evaluation.py` to evaluate the model.
+
+5. Use K-fold cross-validation:
+   - `kfcValidate.py` provides the implementation for K-fold cross-validation.
+
+## Contributions
+
+Pull requests and issues are welcome to help improve the project's features and documentation.
+
+## License
+
+This project is licensed under the MIT License. For details, please refer to the LICENSE file.
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..22e1df79bd8c183836d5c726a79905bbd703ed5b
--- /dev/null
+++ b/README.md
@@ -0,0 +1,52 @@
+
+
+# Detect-AI
+
+Detect-AI 是一个用于检测和分类人工智能生成文本的项目。该项目结合了深度学习和传统统计方法，利用 BERT 模型和统计特征进行文本分析。
+
+## 特性
+
+- 使用 BERT 提取文本语义特征。
+- 提取统计特征并结合 LSTM 进行深度特征融合。
+- 支持传统机器学习模型对比分析。
+- 提供模型保存与加载功能，便于训练与部署。
+
+## 项目结构
+
+- `src/dev/ClassifyModel.py`: 实现模型定义与特征融合逻辑。
+- `src/dev/FeatExtractor.py`: 提供统计特征提取功能。
+- `src/dev/comparison.py`: 支持传统机器学习模型与深度学习模型对比。
+- `src/dev/data.py`: 数据集定义与数据加载逻辑。
+- `src/dev/load_save.py`: 提供模型保存与加载工具函数。
+- `src/dev/kfcValidate.py`: 实现 K 折交叉验证。
+- `src/dev/train.py`: 训练流程核心代码。
+- `src/dev/evaluation.py`: 模型评估逻辑。
+- `src/dev/configs.py`: 全局配置信息。
+- `training/data/train/alldata.jsonl`: 数据集文件。
+
+## 使用方法
+
+1. 安装依赖：
+   ```bash
+   pip install torch transformers scikit-learn
+   ```
+
+2. 准备数据：
+   - 数据格式为 JSONL，存储在 `training/data/train/` 目录下。
+
+3. 训练模型：
+   - 使用 `train.py` 启动训练流程，具体参数可通过配置文件调整。
+
+4. 模型评估：
+   - 使用 `evaluation.py` 进行模型评估。
+
+5. 使用 K 折交叉验证：
+   - `kfcValidate.py` 提供了 K 折交叉验证的实现。
+
+## 贡献
+
+欢迎提交 PR 和 Issue，共同完善项目功能与文档。
+
+## 许可证
+
+本项目基于 MIT 许可证。详情请查看 LICENSE 文件。
\ No newline at end of file