Update handler.py

handler.py

@@ -12,7 +12,7 @@ class EndpointHandler():
         self.model = Llama(model_path="/repository/iubaris-13b-v3_ggml_Q4_K_S.bin", n_ctx=4000, n_gpu_layers=50, n_threads=cpu_count, verbose=True)
 
     def get_input_token_length(self, message: str) -> int:
-        input_ids = self.model([message.encode('utf-8')]
+        input_ids = self.model([message.encode('utf-8')])
         return len(input_ids)    
 
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]: