diff --git a/modelscope/models/cv/shop_segmentation/head_fpn.py b/modelscope/models/cv/shop_segmentation/head_fpn.py
index dfa284d4..0d4027cb 100644
--- a/modelscope/models/cv/shop_segmentation/head_fpn.py
+++ b/modelscope/models/cv/shop_segmentation/head_fpn.py
@@ -9,8 +9,8 @@ import numpy as np
 import torch
 import torch.nn as nn
 from mmcv.cnn import ConvModule
-from timm.layers.drop import drop_path
-from timm.layers.weight_init import trunc_normal_
+from timm.models.layers.drop import drop_path
+from timm.models.layers.weight_init import trunc_normal_
 
 from .common import Upsample, resize
 
diff --git a/modelscope/models/cv/shop_segmentation/models.py b/modelscope/models/cv/shop_segmentation/models.py
index 1b07a08c..a206e9f1 100644
--- a/modelscope/models/cv/shop_segmentation/models.py
+++ b/modelscope/models/cv/shop_segmentation/models.py
@@ -11,8 +11,8 @@ from collections import OrderedDict
 import torch
 import torch.nn.functional as F
 import torch.utils.checkpoint as checkpoint
-from timm.layers.drop import drop_path
-from timm.layers.weight_init import trunc_normal_
+from timm.models.layers.drop import drop_path
+from timm.models.layers.weight_init import trunc_normal_
 from torch import nn
 
 
diff --git a/modelscope/models/cv/shop_segmentation/neck_fpn.py b/modelscope/models/cv/shop_segmentation/neck_fpn.py
index 12c11d76..d344de71 100644
--- a/modelscope/models/cv/shop_segmentation/neck_fpn.py
+++ b/modelscope/models/cv/shop_segmentation/neck_fpn.py
@@ -8,8 +8,8 @@
 import torch.nn as nn
 import torch.nn.functional as F
 from mmcv.cnn import ConvModule
-from timm.layers.drop import drop_path
-from timm.layers.weight_init import trunc_normal_
+from timm.models.layers.drop import drop_path
+from timm.models.layers.weight_init import trunc_normal_
 
 from .common import resize
 
diff --git a/modelscope/models/multi_modal/ofa/tokenization_ofa.py b/modelscope/models/multi_modal/ofa/tokenization_ofa.py
index 77de7a1d..ea79a327 100644
--- a/modelscope/models/multi_modal/ofa/tokenization_ofa.py
+++ b/modelscope/models/multi_modal/ofa/tokenization_ofa.py
@@ -183,6 +183,12 @@ class OFATokenizerZH(PreTrainedTokenizer):
                  tokenize_chinese_chars=True,
                  strip_accents=None,
                  **kwargs):
+        if not os.path.isfile(vocab_file):
+            raise ValueError(
+                f"Can't find a vocabulary file at path '{vocab_file}'. To load the vocabulary from a Google pretrained "
+                'model use `tokenizer = BertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`'
+            )
+        self.vocab = load_vocab(vocab_file)
         super().__init__(
             do_lower_case=do_lower_case,
             do_basic_tokenize=do_basic_tokenize,
@@ -199,12 +205,6 @@ class OFATokenizerZH(PreTrainedTokenizer):
             **kwargs,
         )
 
-        if not os.path.isfile(vocab_file):
-            raise ValueError(
-                f"Can't find a vocabulary file at path '{vocab_file}'. To load the vocabulary from a Google pretrained "
-                'model use `tokenizer = BertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`'
-            )
-        self.vocab = load_vocab(vocab_file)
         self.ids_to_tokens = collections.OrderedDict([
             (ids, tok) for tok, ids in self.vocab.items()
         ])