diff --git a/modelscope/hub/t_jy.py b/modelscope/hub/t_jy.py
new file mode 100644
index 00000000..baf84f46
--- /dev/null
+++ b/modelscope/hub/t_jy.py
@@ -0,0 +1,16 @@
+def dec(param1):
+    print(param1)
+
+    def in_dec(func):
+        def in_func(name):
+            return func(name)
+        return in_func
+    return in_dec
+
+
+@dec("dec1")
+def aa(param):
+    print(param)
+    return
+
+aa("heell")
\ No newline at end of file
diff --git a/modelscope/models/base/base_model.py b/modelscope/models/base/base_model.py
index 1ca7e030..721478c3 100644
--- a/modelscope/models/base/base_model.py
+++ b/modelscope/models/base/base_model.py
@@ -131,6 +131,8 @@ class Model(ABC):
 
         if not hasattr(model, 'cfg'):
             model.cfg = cfg
+
+        model.name = model_name_or_path
         return model
 
     def save_pretrained(self,
diff --git a/modelscope/pipelines/base.py b/modelscope/pipelines/base.py
index 9280cc09..b9a4a25c 100644
--- a/modelscope/pipelines/base.py
+++ b/modelscope/pipelines/base.py
@@ -152,8 +152,9 @@ class Pipeline(ABC):
                  **kwargs) -> Union[Dict[str, Any], Generator]:
         # model provider should leave it as it is
         # modelscope library developer will handle this function
-        model_name = self.cfg.model.type
-        create_library_statistics("pipeline", model_name, None)
+        for single_model in self.models:
+            if hasattr(single_model, 'name'):
+                create_library_statistics("pipeline", single_model.name, None)
         # place model to cpu or gpu
         if (self.model or (self.has_multiple_models and self.models[0])):
             if not self._model_prepare:
diff --git a/modelscope/trainers/trainer.py b/modelscope/trainers/trainer.py
index 522405ff..2e79667f 100644
--- a/modelscope/trainers/trainer.py
+++ b/modelscope/trainers/trainer.py
@@ -437,8 +437,8 @@ class EpochBasedTrainer(BaseTrainer):
 
     def train(self, checkpoint_path=None, *args, **kwargs):
         self._mode = ModeKeys.TRAIN
-        model_name = self.cfg.model.type
-        create_library_statistics("train", model_name, None)
+        if hasattr(self.model, 'name'):
+            create_library_statistics("train", self.model.name, None)
 
         if self.train_dataset is None:
             self.train_dataloader = self.get_train_dataloader()
@@ -459,8 +459,8 @@ class EpochBasedTrainer(BaseTrainer):
         self.train_loop(self.train_dataloader)
 
     def evaluate(self, checkpoint_path=None):
-        model_name = self.cfg.model.type
-        create_library_statistics("evaluate", model_name, None)
+        if hasattr(self.model, 'name'):
+            create_library_statistics("evaluate", self.model.name, None)
         if checkpoint_path is not None and os.path.isfile(checkpoint_path):
             from modelscope.trainers.hooks import CheckpointHook
             CheckpointHook.load_checkpoint(checkpoint_path, self)