Update README.md

README.md

@@ -194,7 +194,7 @@ Trade-off between performance and speed under different confidence thresholds τ
     Our training setting is:
 
     <p align="center">
-        <img src="https://huggingface.co/OpenGVLab/SDLM-32B-D4/resolve/main/assets/hyper-param.png" width="50%"></a>
+        <img src="https://github.com/OpenGVLab/SDLM/blob/main/assets/hyper-param.png" width="50%"></a>
     </p>
 
     The training loss of our 3B model. loss_pos_`i` refers to the loss at the `i`-th position of each block. The loss at `i=0` is close to the SFT loss of AR's NTP.
@@ -214,7 +214,7 @@ Trade-off between performance and speed under different confidence thresholds τ
     | :-- | :-- | :-- | :-- | :-- | :-- | :-- | :-- |
     | loss_pos_1 | loss_pos_2 | loss_pos_3 | loss_pos_4 | -- | -- | -- | -- |
 
-    ![](https://huggingface.co/OpenGVLab/SDLM-32B-D4/resolve/main/assets/train_log_3b.png)
+    ![](https://github.com/OpenGVLab/SDLM/blob/main/assets/train_log_3b.png)
 
 ## Evaluation
 
@@ -223,7 +223,7 @@ Currently, we use [Opencompass](https://github.com/open-compass/opencompass) for
 ## Case
 
 <p align="center">
-    <img src="https://huggingface.co/OpenGVLab/SDLM-32B-D4/resolve/main/assets/case.gif" width="70%"></a>
+    <img src="https://github.com/OpenGVLab/SDLM/blob/main/assets/case.gif" width="70%"></a>
 </p>
 
 ## Acknowledge