diff --git a/litellm/llms/huggingface_restapi.py b/litellm/llms/huggingface_restapi.py
index c347910f8..2f9485963 100644
--- a/litellm/llms/huggingface_restapi.py
+++ b/litellm/llms/huggingface_restapi.py
@@ -584,6 +584,14 @@ class Huggingface(BaseLLM):
                             "embedding": embedding # flatten list returned from hf
                         }
                     )
+                elif isinstance(embedding, list) and isinstance(embedding[0], float):
+                    output_data.append(
+                        {
+                            "object": "embedding",
+                            "index": idx,
+                            "embedding": embedding # flatten list returned from hf
+                        }
+                    )
                 else: 
                     output_data.append(
                         {
diff --git a/litellm/main.py b/litellm/main.py
index 16ce2850c..31613a67a 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -1748,8 +1748,7 @@ async def aembedding(*args, **kwargs):
             or custom_llm_provider == "anyscale"
             or custom_llm_provider == "openrouter"
             or custom_llm_provider == "deepinfra"
-            or custom_llm_provider == "perplexity"
-            or custom_llm_provider == "huggingface"): # currently implemented aiohttp calls for just azure and openai, soon all. 
+            or custom_llm_provider == "perplexity"): # currently implemented aiohttp calls for just azure and openai, soon all. 
             # Await normally
             init_response = await loop.run_in_executor(None, func_with_context)
             if isinstance(init_response, dict) or isinstance(init_response, ModelResponse): ## CACHING SCENARIO