diff --git a/docs/doc/en/faq.md b/docs/doc/en/faq.md
index a05632f3..59b90ce0 100644
--- a/docs/doc/en/faq.md
+++ b/docs/doc/en/faq.md
@@ -45,3 +45,10 @@ It is not recommended to use cameras or screens other than the officially bundle
 The officially bundled accessories have been fine-tuned for both software and hardware, ensuring the best performance and allowing for out-of-the-box usage. Other accessories may have different interfaces, drivers, and software, requiring you to calibrate them yourself, which is an extremely complex process.
 
 However, if you are an expert, we welcome you to submit a pull request!
+
+## Model running error: cvimodel built for xxxcv181x CANNOT run on platform cv181x.
+
+Failure to parse the model file is generally caused by file corruption. Ensure that your model file is not damaged. For example:
+* If it was downloaded from the internet, make sure the download was not corrupted. Typically, files on the internet provide sha256sum/md5 checksums. After downloading, you can compare these values; for specific methods, please search online or ask ChatGPT.
+* If it comes from a compressed archive, ensure that the decompression process was error-free. You can decompress the archive again to make sure there were no errors in the process.
+* Ensure that the file was not damaged during the transfer to the device. You can compare the sha256sum values of the file on the device and on your computer; for specific methods, please search online or ask ChatGPT.
\ No newline at end of file
diff --git a/docs/doc/zh/faq.md b/docs/doc/zh/faq.md
index c28e52ab..af260b29 100644
--- a/docs/doc/zh/faq.md
+++ b/docs/doc/zh/faq.md
@@ -49,4 +49,11 @@ MaixPy 目前仅支持 MaixCAM 系列板子，其它同款芯片的板子也不
 
 
 
+## 运行模型报错 cvimodel built for xxxcv181x CANNOT run on platform cv181x
+
+解析模型文件失败了，一般情况是模型文件损坏造成的，确保你的模型文件是没有损坏的。
+比如：
+* 如果是从网上下载的，保证下载没有出问题，一般网上的文件提供 sha256sum/md5 校验值，下载下来后可以对比一下，具体方法请自行搜索或者问 ChatGPT。
+* 如果是来自压缩包，请确认解压过程没有出错，可以从压缩包重新解压一遍保证中间没有出错。
+* 保证传输到设备的过程没有造成文件损坏，可以对比一下设备中的文件和电脑中的文件 sha256sum 值，具体方法请自性搜索或者问 ChatGPT。