Update app.py

app.py

@@ -71,19 +71,14 @@ def generate_response(message, history, temperature, max_new_tokens):
             partial_message += new_text
             yield partial_message.strip()
 
-    except RuntimeError as e:
-        if "CUDA out of memory" in str(e):
-            yield "GPU memory exceeded. Try reducing the max tokens or using a smaller model."
-        else:
-            yield f"An error occurred: {str(e)}"
     except Exception as e:
-        yield f"An unexpected error occurred: {str(e)}"
+        yield f"An error occurred: {str(e)}"
 
 css = """
   #output {
-    height: 1100px; 
+    height: 1000px; 
     overflow: auto; 
-    border: 3px solid #ccc; 
+    border: 2px solid #ccc; 
   }
 """