max new token update

app.py

@@ -49,7 +49,7 @@ async def ask(request: Request):
     print("Tokenizer process completed")
 
     print("Model process started")
-    outputs = model.generate(**input_ids, max_new_tokens=256)
+    outputs = model.generate(**input_ids, max_new_tokens=512)
 
     print("Tokenizer decode process started")
     answer = tokenizer.decode(outputs[0]).split("<end_of_turn>")[1].strip()