Update app.py

app.py

@@ -58,6 +58,9 @@ def generate(
     )
     seed = seed + 1
     formatted_prompt = format_prompt(prompt, history, system_prompt)
+    status = client.get_model_status()
+    if not status.loaded:
+        client = client2 
 
     try:
         stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
@@ -73,22 +76,7 @@ def generate(
                     yield output
             yield output
     except Exception as e:
-        raise gr.Error(f"Client 1 error while generating: {e}")
-        try:
-            stream = client2.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-            output = ""
-
-            for response in stream:
-                output += response.token.text
-    
-                for stop_str in STOP_SEQUENCES:
-                    if output.endswith(stop_str):
-                        output = output[:-len(stop_str)]
-#                        output = output.rstrip()
-                        yield output
-                yield output
-        except Exception as e:
-            raise gr.Error(f"Client 2 error while generating: {e}")
+        raise gr.Error(f"Client error while generating: {e}")
     return output
 
 additional_inputs=[