Update app.py

app.py

@@ -294,13 +294,15 @@ def generate(text, history, rag_option, model_option,  temperature=0.5, max_new_
         #inference allg:
         data = {
             "inputs": prompt,
-            "options": {"max_new_tokens": 1024},
+            "options": {"max_new_tokens": max_new_tokens},
         }
         response= requests.post(API_URL, headers=HEADERS, json=data)
         result = response.json()
         print("result:------------------")
         chatbot_response = result[0]['generated_text']
         print(chatbot_response)
+        print("anzahl tokens gesamt antwort:------------------")
+        print (len(response.split()))
     except Exception as e:
         raise gr.Error(e)
 
@@ -309,7 +311,7 @@ def generate(text, history, rag_option, model_option,  temperature=0.5, max_new_
     
     #Antwort als Stream ausgeben... 
     for i in range(len(chatbot_message)):
-        time.sleep(0.05)
+        time.sleep(0.03)
         yield  chatbot_message[: i+1]