diff --git a/llama_stack/templates/nvidia/nvidia.py b/llama_stack/templates/nvidia/nvidia.py
index a505a1b93..56d13a09a 100644
--- a/llama_stack/templates/nvidia/nvidia.py
+++ b/llama_stack/templates/nvidia/nvidia.py
@@ -41,9 +41,11 @@ def get_distribution_template() -> DistributionTemplate:
     core_model_to_hf_repo = {m.descriptor(): m.huggingface_repo for m in all_registered_models()}
     default_models = [
         ModelInput(
-            model_id=core_model_to_hf_repo[m.llama_model],
+            model_id=core_model_to_hf_repo[m.llama_model] if m.llama_model else m.provider_model_id,
             provider_model_id=m.provider_model_id,
             provider_id="nvidia",
+            model_type=m.model_type,
+            metadata=m.metadata,
         )
         for m in _MODEL_ENTRIES
     ]
diff --git a/tests/client-sdk/inference/test_embedding.py b/tests/client-sdk/inference/test_embedding.py
index 6b0ddd74d..9b807341e 100644
--- a/tests/client-sdk/inference/test_embedding.py
+++ b/tests/client-sdk/inference/test_embedding.py
@@ -45,16 +45,14 @@
 #
 
 import pytest
-
 from llama_stack_client.types import EmbeddingsResponse
 from llama_stack_client.types.shared.interleaved_content import (
-    TextContentItem,
+    URL,
     ImageContentItem,
     ImageContentItemImage,
-    URL,
+    TextContentItem,
 )
 
-
 DUMMY_STRING = "hello"
 DUMMY_STRING2 = "world"
 DUMMY_TEXT = TextContentItem(text=DUMMY_STRING, type="text")