added output tab_name

app.py

@@ -63,7 +63,7 @@ def vicuna_respond(tab_name, message, chat_history):
         
     chat_history.append((formatted_prompt, bot_message))
     time.sleep(2)
-    return "", chat_history
+    return tab_name, "", chat_history
 
 def llama_respond(tab_name, message, chat_history):
     formatted_prompt = f'''Generate the output only for the assistant. Please output any <{tab_name}> in the following sentence one per line without any additional text: <{message}>'''
@@ -73,16 +73,7 @@ def llama_respond(tab_name, message, chat_history):
         
     chat_history.append((formatted_prompt, bot_message))
     time.sleep(2)
-    return "", chat_history
-
-def vicuna_respond(message, chat_history):
-    input_ids = vicuna_tokenizer.encode(message, return_tensors="pt")
-    output_ids = vicuna_model.generate(input_ids, max_length=50, num_beams=5, no_repeat_ngram_size=2)
-    bot_message = vicuna_tokenizer.decode(output_ids[0], skip_special_tokens=True)
-        
-    chat_history.append((message, bot_message))
-    time.sleep(2)
-    return "", chat_history
+    return tab_name, "", chat_history
 
 def interface():
         gr.Markdown(" Description ")