diff --git a/litellm/llms/huggingface_restapi.py b/litellm/llms/huggingface_restapi.py
index da5f7bebea..ec35532af5 100644
--- a/litellm/llms/huggingface_restapi.py
+++ b/litellm/llms/huggingface_restapi.py
@@ -375,9 +375,19 @@ def embedding(
     else:
         embed_url = f"https://api-inference.huggingface.co/models/{model}"
     
-    data = {
-        "inputs": input
-    }
+    if "sentence-transformers" in model: 
+        if len(input) == 0: 
+            raise HuggingfaceError(status_code=400, message="sentence transformers requires 2+ sentences")
+        data = {
+            "inputs": {
+                "source_sentence": input[0], 
+                "sentences": [ "That is a happy dog", "That is a very happy person", "Today is a sunny day" ]
+            }
+        }
+    else:
+        data = {
+            "inputs": input
+        }
     
     ## LOGGING
     logging_obj.pre_call(
@@ -402,15 +412,38 @@ def embedding(
 
     embeddings = response.json()
 
+    if "error" in embeddings: 
+        raise HuggingfaceError(status_code=500, message=embeddings['error'])
+    
     output_data = []
-    for idx, embedding in enumerate(embeddings):
-        output_data.append(
+    print(f"embeddings: {embeddings}")
+    if "similarities" in embeddings: 
+        for idx, embedding in embeddings["similarities"]:
+            output_data.append(
             {
                 "object": "embedding",
                 "index": idx,
-                "embedding": embedding[0][0] # flatten list returned from hf
+                "embedding": embedding # flatten list returned from hf
             }
         )
+    else: 
+        for idx, embedding in enumerate(embeddings):
+            if isinstance(embedding, float): 
+                output_data.append(
+                    {
+                        "object": "embedding",
+                        "index": idx,
+                        "embedding": embedding # flatten list returned from hf
+                    }
+                )
+            else: 
+                output_data.append(
+                    {
+                        "object": "embedding",
+                        "index": idx,
+                        "embedding": embedding[0][0] # flatten list returned from hf
+                    }
+                )
     model_response["object"] = "list"
     model_response["data"] = output_data
     model_response["model"] = model
diff --git a/litellm/tests/test_embedding.py b/litellm/tests/test_embedding.py
index d7bf867ab4..10c2ce8b20 100644
--- a/litellm/tests/test_embedding.py
+++ b/litellm/tests/test_embedding.py
@@ -89,17 +89,17 @@ def test_bedrock_embedding():
 # test_bedrock_embedding()
 
 # comment out hf tests - since hf endpoints are unstable
-# def test_hf_embedding():
-#     try:
-#         # huggingface/microsoft/codebert-base
-#         # huggingface/facebook/bart-large
-#         response = embedding(
-#             model="huggingface/BAAI/bge-large-zh", input=["good morning from litellm", "this is another item"]
-#         )
-#         print(f"response:", response)
-#     except Exception as e:
-#         pytest.fail(f"Error occurred: {e}")
-# test_hf_embedding()
+def test_hf_embedding():
+    try:
+        # huggingface/microsoft/codebert-base
+        # huggingface/facebook/bart-large
+        response = embedding(
+            model="huggingface/sentence-transformers/all-MiniLM-L6-v2", input=["good morning from litellm", "this is another item"]
+        )
+        print(f"response:", response)
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+test_hf_embedding()
 
 # test async embeddings
 def test_aembedding():