diff --git a/src/transformers/models/auto/modeling_auto.py b/src/transformers/models/auto/modeling_auto.py
index caa4c9d4df..7f4968d03c 100644
--- a/src/transformers/models/auto/modeling_auto.py
+++ b/src/transformers/models/auto/modeling_auto.py
@@ -771,6 +771,13 @@ MODEL_FOR_AUDIO_XVECTOR_MAPPING_NAMES = OrderedDict(
     ]
 )
 
+_MODEL_FOR_ZERO_SHOT_IMAGE_CLASSIFICATION_MAPPING_NAMES = OrderedDict(
+    [
+        # Model for Zero Shot Image Classification mapping
+        ("clip", "CLIPModel"),
+    ]
+)
+
 MODEL_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, MODEL_MAPPING_NAMES)
 MODEL_FOR_PRETRAINING_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, MODEL_FOR_PRETRAINING_MAPPING_NAMES)
 MODEL_WITH_LM_HEAD_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, MODEL_WITH_LM_HEAD_MAPPING_NAMES)
diff --git a/utils/update_metadata.py b/utils/update_metadata.py
index 5ccd07aeb7..aaf296c043 100644
--- a/utils/update_metadata.py
+++ b/utils/update_metadata.py
@@ -91,6 +91,11 @@ PIPELINE_TAGS_AND_AUTO_MODELS = [
         "AutoModelForVisualQuestionAnswering",
     ),
     ("image-to-text", "MODEL_FOR_FOR_VISION_2_SEQ_MAPPING_NAMES", "AutoModelForVision2Seq"),
+    (
+        "zero-shot-image-classification",
+        "_MODEL_FOR_ZERO_SHOT_IMAGE_CLASSIFICATION_MAPPING_NAMES",
+        "AutoModel",
+    ),
 ]