diff --git a/modelscope/pipelines/builder.py b/modelscope/pipelines/builder.py
index 743ba1cb..eaa6d1c8 100644
--- a/modelscope/pipelines/builder.py
+++ b/modelscope/pipelines/builder.py
@@ -74,7 +74,7 @@ DEFAULT_MODEL_FOR_PIPELINE = {
                            'damo/cv_resnet50_video-category'),
     Tasks.multi_modal_embedding:
     (Pipelines.multi_modal_embedding,
-     'damo/multi-modal_clip-vit-large-patch14-chinese_multi-modal-embedding'),
+     'damo/multi-modal_clip-vit-large-patch14_zh'),
     Tasks.generative_multi_modal_embedding:
     (Pipelines.generative_multi_modal_embedding,
      'damo/multi-modal_gemm-vit-large-patch14_generative-multi-modal-embedding'
diff --git a/tests/pipelines/test_multi_modal_embedding.py b/tests/pipelines/test_multi_modal_embedding.py
index 001bf951..3bf3af87 100644
--- a/tests/pipelines/test_multi_modal_embedding.py
+++ b/tests/pipelines/test_multi_modal_embedding.py
@@ -11,7 +11,7 @@ from modelscope.utils.test_utils import test_level
 
 
 class MultiModalEmbeddingTest(unittest.TestCase):
-    model_id = 'damo/multi-modal_clip-vit-large-patch14-chinese_multi-modal-embedding'
+    model_id = 'damo/multi-modal_clip-vit-large-patch14_zh'
     test_text = {'text': '一张风景图'}
 
     @unittest.skipUnless(test_level() >= 2, 'skip test in current test level')
diff --git a/tests/trainers/test_clip_multi_modal_embedding_trainer.py b/tests/trainers/test_clip_multi_modal_embedding_trainer.py
index c1b51ec6..03f82854 100644
--- a/tests/trainers/test_clip_multi_modal_embedding_trainer.py
+++ b/tests/trainers/test_clip_multi_modal_embedding_trainer.py
@@ -24,7 +24,7 @@ def clip_train_worker(local_rank, ngpus, node_size, node_rank):
     dist.init_process_group(
         backend='nccl', world_size=dist_world_size, rank=global_rank)
 
-    model_id = 'damo/multi-modal_clip-vit-large-patch14-chinese_multi-modal-embedding'
+    model_id = 'damo/multi-modal_clip-vit-large-patch14_zh'
     local_model_dir = snapshot_download(model_id)
 
     default_args = dict(