Update app.py

app.py

@@ -55,9 +55,9 @@ def predict(text, seed, out_seq_length, min_gen_length, sampling_strategy,
 if __name__ == "__main__":
 
     en_fil = ['The Starry Night is an oil-on-canvas painting by [MASK] in June 1889.']
-    en_gen = ['Eight planets in solar system are']
+    en_gen = ['Eight planets in solar system are [gMASK]']
     ch_fil = ['凯旋门位于意大利米兰市古城堡旁。1807年为纪念[MASK]而建，门高25米，顶上矗立两武士青铜古兵车铸像。']
-    ch_gen = ['三亚位于海南岛的最南端,是中国最南部的热带滨海旅游城市']
+    ch_gen = ['三亚位于海南岛的最南端,是中国最南部的热带滨海旅游城市 [gMASK]']
     en_to_ch = ['Pencil in Chinese is [MASK].']
     ch_to_en = ['"我思故我在"的英文是"[MASK]"。']
 
@@ -66,10 +66,9 @@ if __name__ == "__main__":
     with gr.Blocks() as demo:
         gr.Markdown(
             """
-            # GLM-130B
-            An Open Bilingual Pre-Trained Model
-            
-            [Visit our github repo](https://github.com/THUDM/GLM-130B)
+            An Open Bilingual Pre-Trained Model. [Visit our github repo](https://github.com/THUDM/GLM-130B)
+
+            GLM-130B uses two different mask tokens: `[MASK]` for short blank filling and `[gMASK]` for left-to-right long text generation. When the input does not contain any MASK token, `[gMASK]` will be automatically appended to the end of the text. We recommend that you use `[MASK]` to try text fill-in-the-blank to reduce wait time (ideally within seconds without queuing).
             """)
 
         with gr.Row():