Update app.py

app.py

@@ -74,7 +74,7 @@ if __name__ == "__main__":
             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).
             
-            Note: We suspect that there is a bug in the current FasterTransformer INT4 implementation that leads to gaps in the output compared to the FP16 model (e.g. more repititions), which we are troubleshooting, and the current model output is **for reference only**
+            Note: We suspect that there is a bug in the current FasterTransformer INT4 implementation that leads to gaps in generations compared to the FP16 model (e.g. more repititions), which we are troubleshooting, and the current model output is **for reference only**
             """)
 
         with gr.Row():