Update app.py

app.py

@@ -271,9 +271,7 @@ def predict(
             response = strip_stop_words(full_response, stop_words)
             conversation.update_last_message(response)
             gradio_chatbot_output[-1][1] = response
-            yield gradio_chatbot_output, to_gradio_history(
-                conversation
-            ), "Generating..."
+            yield gradio_chatbot_output, #to_gradio_history(conversation), "Generating..."
 
     print("flushed result to gradio")
     torch.cuda.empty_cache()
@@ -284,7 +282,7 @@ def predict(
             f"temperature: {temperature}, top_p: {top_p}, repetition_penalty: {repetition_penalty}, max_length_tokens: {max_length_tokens}"
         )
 
-    yield gradio_chatbot_output, to_gradio_history(conversation), "Generate: Success"
+    yield gradio_chatbot_output,, "Generate: Success",# to_gradio_history(conversation)
 
 
 def retry(