token size decreased for llm

utils/helper_functions.py

@@ -226,7 +226,7 @@ def llama2_7b_ysa(prompt: str) -> str:
     # Define the query payload with the prompt and any additional parameters
     query_payload: Dict[str, Any] = {
         "inputs": prompt,
-        "parameters": {"max_new_tokens": 200},
+        "parameters": {"max_new_tokens": 30},
     }
 
     # Send the query to the model and store the output response