docs: update readme

README.md

@@ -104,7 +104,7 @@ pip install detectron2 --extra-index-url https://myhloli.github.io/wheels/
 
 #### 2. Downloading model weights files
 
-For detailed references, please see below[how_to_download_models](docs/how_to_download_models_en.md)
+For detailed references, please see below [how_to_download_models](docs/how_to_download_models_en.md)
 
 After downloading the model weights, move the 'models' directory to a directory on a larger disk space, preferably an SSD.
 
@@ -151,8 +151,8 @@ magic-pdf --help
 ##### CUDA
 
 You need to install the corresponding PyTorch version according to your CUDA version.  
+This example installs the CUDA 11.8 version.More information https://pytorch.org/get-started/locally/  
 ```bash
-# When using the GPU solution, you need to reinstall PyTorch for the corresponding CUDA version. This example installs the CUDA 11.8 version.
 pip install --force-reinstall torch==2.3.1 torchvision==0.18.1 --index-url https://download.pytorch.org/whl/cu118
 ```
 Also, you need to modify the value of "device-mode" in the configuration file magic-pdf.json.  
@@ -166,7 +166,6 @@ Also, you need to modify the value of "device-mode" in the configuration file ma
 
 For macOS users with M-series chip devices, you can use MPS for inference acceleration.  
 You also need to modify the value of "device-mode" in the configuration file magic-pdf.json.  
-
 ```json
 {
   "device-mode":"mps"

README_zh-CN.md

@@ -90,7 +90,7 @@ pip install magic-pdf
 ```bash
 pip install magic-pdf[full-cpu]
 ```
-高精度模型依赖于detectron2，该库需要编译安装，如需自行编译，请参考https://github.com/facebookresearch/detectron2/issues/5114
+高精度模型依赖于detectron2，该库需要编译安装，如需自行编译，请参考 https://github.com/facebookresearch/detectron2/issues/5114  
 或是直接使用我们预编译的whl包(仅限python 3.10)：  
 ```bash
 pip install detectron2 --extra-index-url https://myhloli.github.io/wheels/
@@ -98,11 +98,11 @@ pip install detectron2 --extra-index-url https://myhloli.github.io/wheels/
 
 #### 2. 下载模型权重文件
 
-详细参考[如何下载模型文件](docs/how_to_download_models_zh_cn.md)
+详细参考 [如何下载模型文件](docs/how_to_download_models_zh_cn.md)  
 下载后请将models目录移动到空间较大的ssd磁盘目录  
 
 #### 3. 拷贝配置文件并进行配置
-在仓库根目录可以获得[magic-pdf.template.json](magic-pdf.template.json)文件
+在仓库根目录可以获得 [magic-pdf.template.json](magic-pdf.template.json) 文件
 ```bash
 cp magic-pdf.template.json ~/magic-pdf.json
 ```
@@ -139,8 +139,8 @@ magic-pdf --help
 ###### CUDA
 
 需要根据自己的CUDA版本安装对应的pytorch版本  
+以下是对应CUDA 11.8版本的安装命令，更多信息请参考 https://pytorch.org/get-started/locally/  
 ```bash
-# 使用gpu方案时，需要重新安装对应cuda版本的pytorch，例子是安装CUDA 11.8版本的
 pip install --force-reinstall torch==2.3.1 torchvision==0.18.1 --index-url https://download.pytorch.org/whl/cu118
 ```
 
@@ -153,7 +153,6 @@ pip install --force-reinstall torch==2.3.1 torchvision==0.18.1 --index-url https
 
 ###### MPS
 使用macOS(M系列芯片设备)可以使用MPS进行推理加速  
-
 需要修改配置文件magic-pdf.json中"device-mode"的值  
 ```json
 {