diff --git a/TensorFlow/built-in/nlp/Transformer_ID0004_for_TensorFlow/README.md b/TensorFlow/built-in/nlp/Transformer_ID0004_for_TensorFlow/README.md
index 2bce93c95fce2b129c6254bf0534eb245a34b405..f1a0216439dcd90213d649b4371999fa25c00f49 100644
--- a/TensorFlow/built-in/nlp/Transformer_ID0004_for_TensorFlow/README.md
+++ b/TensorFlow/built-in/nlp/Transformer_ID0004_for_TensorFlow/README.md
@@ -111,7 +111,7 @@ run_config = NPURunConfig(
 <h2 id="训练环境准备.md">训练环境准备</h2>
 
 1.  硬件环境准备请参见各硬件产品文档"[驱动和固件安装升级指南]( https://support.huawei.com/enterprise/zh/category/ai-computing-platform-pid-1557196528909)"。需要在硬件设备上安装与CANN版本配套的固件与驱动。_
-2.  宿主机上需要安装Docker并登录[Ascend Hub中心](https://ascendhub.huawei.com/#/detail?name=ascend-tensorflow-arm)获取镜像。
+2.  宿主机上需要安装Docker并登录[Ascend Hub中心](https://www.hiascend.com/developer/ascendhub/)获取镜像。
 
     当前模型支持的镜像列表如[表1](#zh-cn_topic_0000001074498056_table1519011227314)所示。
 
@@ -126,11 +126,11 @@ run_config = NPURunConfig(
     </th>
     </tr>
     </thead>
-    <tbody><tr id="zh-cn_topic_0000001074498056_row71915221134"><td class="cellrowborder" valign="top" width="47.32%" headers="mcps1.2.4.1.1 "><a name="zh-cn_topic_0000001074498056_ul81691515131910"></a><a name="zh-cn_topic_0000001074498056_ul81691515131910"></a><ul id="zh-cn_topic_0000001074498056_ul81691515131910"><li><em id="i82326495129"><a name="i82326495129"></a><a name="i82326495129"></a>ARM架构：<a href="https://ascend.huawei.com/ascendhub/#/detail?name=ascend-tensorflow-arm" target="_blank" rel="noopener noreferrer">ascend-tensorflow-arm</a></em></li><li><em id="i18233184918125"><a name="i18233184918125"></a><a name="i18233184918125"></a>x86架构：<a href="https://ascend.huawei.com/ascendhub/#/detail?name=ascend-tensorflow-x86" target="_blank" rel="noopener noreferrer">ascend-tensorflow-x86</a></em></li></ul>
+    <tbody><tr id="zh-cn_topic_0000001074498056_row71915221134"><td class="cellrowborder" valign="top" width="47.32%" headers="mcps1.2.4.1.1 "><a name="zh-cn_topic_0000001074498056_ul81691515131910"></a><a name="zh-cn_topic_0000001074498056_ul81691515131910"></a><ul id="zh-cn_topic_0000001074498056_ul81691515131910"><li><em id="i82326495129"><a name="i82326495129"></a><a name="i82326495129"></a>ARM架构：ascend-tensorflow-arm</em></li><li><em id="i18233184918125"><a name="i18233184918125"></a><a name="i18233184918125"></a>x86架构：ascend-tensorflow-x86</em></li></ul>
     </td>
     <td class="cellrowborder" valign="top" width="25.52%" headers="mcps1.2.4.1.2 "><p id="zh-cn_topic_0000001074498056_p1450714271532"><a name="zh-cn_topic_0000001074498056_p1450714271532"></a><a name="zh-cn_topic_0000001074498056_p1450714271532"></a><em id="i72359495125"><a name="i72359495125"></a><a name="i72359495125"></a>20.2.0</em></p>
     </td>
-    <td class="cellrowborder" valign="top" width="27.16%" headers="mcps1.2.4.1.3 "><p id="zh-cn_topic_0000001074498056_p18244640152312"><a name="zh-cn_topic_0000001074498056_p18244640152312"></a><a name="zh-cn_topic_0000001074498056_p18244640152312"></a><em id="i162363492129"><a name="i162363492129"></a><a name="i162363492129"></a><a href="https://support.huawei.com/enterprise/zh/ascend-computing/cann-pid-251168373/software" target="_blank" rel="noopener noreferrer">20.2</a></em></p>
+    <td class="cellrowborder" valign="top" width="27.16%" headers="mcps1.2.4.1.3 "><p id="zh-cn_topic_0000001074498056_p18244640152312"><a name="zh-cn_topic_0000001074498056_p18244640152312"></a><a name="zh-cn_topic_0000001074498056_p18244640152312"></a><em id="i162363492129"><a name="i162363492129"></a><a name="i162363492129"></a><a href="https://support.huawei.com/enterprise/zh/ascend-computing/cann-pid-251168373/software" target="_blank" rel="noopener noreferrer">8.0</a></em></p>
     </td>
     </tr>
     </tbody>
@@ -485,4 +485,4 @@ python3.7.5 transformer_online_inference.py
 --batchSize  在线推理的BatchSize
 ```
 
-在线推理由于涉及动态shape的模型编译，时间会比较长；如果是medium的模型，完全执行完约1h
\ No newline at end of file
+在线推理由于涉及动态shape的模型编译，时间会比较长；如果是medium的模型，完全执行完约1h