update

app.py

@@ -50,7 +50,11 @@ def text_generate(prompt):
           "temperature": 1.1,
           "max_new_tokens": 250,
           "return_full_text": True
-          }}
+          }, 
+          "options": 
+          {"use_cache": True,
+          "wait_for_modelche": True
+          },}
   response = requests.post(API_URL, headers=headers, json=json_)
   print(f"Response  is : {response}")
   output = response.json()