Update app.py

app.py

@@ -114,7 +114,7 @@ def talk(prompt, history):
     # the chat template structure should be based on text generation model format
 
 # indicates the end of a sequence
-    stream = model.create_chat_completion(messages = messages, max_tokens=1000, stop=["</s>"], stream=True)
+    stream = model.create_chat_completion(messages = messages, max_tokens=1000, stop=["</s>"], stream=False)
 #    print(f"{stream}")
     print("check 7")
 #    print(stream['choices'][0]['message']['content'])
@@ -135,17 +135,7 @@ def talk(prompt, history):
     # only the tokens comprising the top_p probability mass are considered for responses
     # This output is a data structure containing all the information returned by generate(), but that can also be used as tuple or dictionary.
  
-#    start = time.time()
-#    NUM_TOKENS=0
-
-#    time_generate = time.time() - start
-#    print('\n')
-#    print('-'*4+'End Generation'+'-'*4)
-#    print(f'Num of generated tokens: {NUM_TOKENS}')
- #   print(f'Time for complete generation: {time_generate}s')
- #   print(f'Tokens per secound: {NUM_TOKENS/time_generate}')
- #   print(f'Time per token: {(time_generate/NUM_TOKENS)*1000}ms')
- 
+
     
 TITLE = "AI Copilot for Diabetes Patients"