time

app.py

@@ -1,5 +1,6 @@
 from transformers import pipeline, Conversation
 import gradio as gr
+import time
 
 chatbot = pipeline("text-generation", model="epfl-llm/meditron-7b", use_auth_token=True)
 # chatbot = pipeline("translation", model="facebook/mbart-large-50-many-to-many-mmt", use_auth_token=True)
@@ -8,10 +9,13 @@ message_list = []
 response_list = []
 
 def vanilla_chatbot(message, history):
+    start = time.perf_counter()
     conversation = Conversation(text=message, past_user_inputs=message_list, generated_responses=response_list)
     conversation = chatbot(conversation)
-
-    return conversation.generated_responses[-1]
+    to_return = conversation.generated_responses[-1]
+    
+    print ("%5.1f secs " % (start - time.perf_counter()))
+    return to_return
 
 def chat_bot(message, history):
     return chatbot(message, max_length=500)[0]['generated_text']