Update handler.py

handler.py

@@ -35,6 +35,6 @@ class EndpointHandler():
                 "reason": "max_length was passed as something that was absolutely not a plain old int"
             })
         
-        res = self.model(fmat, temperature=args["temperature"], top_p=args["top_p"], top_k=args["top_k"], max_tokens=args["max_length"])
+        res = self.model(fmat, temperature=args["temperature"], top_p=args["top_p"], top_k=args["top_k"], max_tokens=max_length)
 
         return res