diff --git a/cn_clip/training/main.py b/cn_clip/training/main.py
index b8d20e8..9e09c09 100644
--- a/cn_clip/training/main.py
+++ b/cn_clip/training/main.py
@@ -258,7 +258,16 @@ def main():
         }
         assert args.teacher_model_name in teacher_model_dict, "Error: Valid teacher model name has not been built."
 
-        teacher_model = Model.from_pretrained(args.teacher_model_name)
+        try:
+            teacher_model = Model.from_pretrained(args.teacher_model_name)
+        except Exception as e:
+            if "Unexpected key(s) in state_dict" in str(e):
+                error_message = (
+                    "An error occurred while loading the model: {}\n"
+                    "Maybe you should update modelscope. ".format(e)
+                )
+                raise RuntimeError(error_message)
+
         for k, v in teacher_model.state_dict().items():
             v.requires_grad = False
         
diff --git a/distillation.md b/distillation.md
index a182a4a..e2d2387 100644
--- a/distillation.md
+++ b/distillation.md
@@ -59,5 +59,5 @@
 </p>
 
 
-## Future Action
-将会在阿里云官网上线相关的解决方案的Jupyter Notebook，提供更加清晰的实例教学，敬请期待。
+## 快速体验
+相关解决方案已经上线阿里云[PAI-DSW Gallery](https://gallery.pai-ml.com/#/preview/deepLearning/cv/cn_clip_distillation)。在PAI-DSW Gallery提供对应的Notebook，支持用户利用自有数据构建专属搜索模型。
diff --git a/distillation_En.md b/distillation_En.md
index ddaac11..0de552e 100644
--- a/distillation_En.md
+++ b/distillation_En.md
@@ -9,8 +9,8 @@ Here we provide an example of knowledge distillation for Chinese-CLIP fine-tunin
 + Nvidia GPUs **with Turning, Ampere, Ada or Hopper architecture** (such as H100, A100, RTX 3090, T4, and RTX 2080). Please refer to [this document](https://en.wikipedia.org/wiki/CUDA#GPUs_supported) for the corresponding GPUs of each Nvidia architecture.
 + CUDA 11.4 and above.
 + PyTorch 1.12 and above.
-+ **ModelScope**：Install FlashAttention by executing `pip install modelscope`.
 + Other dependencies as required in [requirements.txt](requirements.txt).
++ **ModelScope**：Install FlashAttention by executing `pip install modelscope`.
 
 ## Use it in Chinese-CLIP!
 It is not complicated to apply knowledge distillation to the image side in Chinese-CLIP finetune. Just add the `--distllation` configuration item to the sh script of finetune.
@@ -56,5 +56,5 @@ Advantages of our approach:
     <img src="examples/image_retrieval_result2.jpg" width="400" /><br>
 </p>
 
-## Future Action
-The Jupyter Notebook of related solutions will be launched on the Alibaba Cloud official website, which will provide a more clear example for usage. Stay tuned for this!
+## Quick Start
+Related solutions have been launched on Alibaba Cloud [PAI-DSW Gallery](https://gallery.pai-ml.com/#/preview/deepLearning/cv/cn_clip_distillation). The corresponding Notebook is provided in PAI-DSW Gallery to support users to build exclusive search models using their own data.