diff --git a/docs/my-website/docs/completion/supported.md b/docs/my-website/docs/completion/supported.md
index f7e835eed..01abbddc9 100644
--- a/docs/my-website/docs/completion/supported.md
+++ b/docs/my-website/docs/completion/supported.md
@@ -49,10 +49,10 @@ Here are some examples of supported models:
 
 | Model Name       | Function Call                                                                       | Required OS Variables                |
 |------------------|-------------------------------------------------------------------------------------|--------------------------------------|
-| [stabilityai/stablecode-completion-alpha-3b-4k](https://huggingface.co/stabilityai/stablecode-completion-alpha-3b-4k)  | `completion(model="stabilityai/stablecode-completion-alpha-3b-4k", messages=messages, hugging_face=True)` | `os.environ['HF_TOKEN']`       |
-| [bigcode/starcoder](https://huggingface.co/bigcode/starcoder)                           | `completion(model="bigcode/starcoder", messages=messages, hugging_face=True)`          | `os.environ['HF_TOKEN']`       |
-| [google/flan-t5-xxl](https://huggingface.co/google/flan-t5-xxl)                         | `completion(model="google/flan-t5-xxl", messages=messages, hugging_face=True)`         | `os.environ['HF_TOKEN']`       |
-| [google/flan-t5-large](https://huggingface.co/google/flan-t5-large)                     | `completion(model="google/flan-t5-large", messages=messages, hugging_face=True)`       | `os.environ['HF_TOKEN']`       |
+| [stabilityai/stablecode-completion-alpha-3b-4k](https://huggingface.co/stabilityai/stablecode-completion-alpha-3b-4k)  | `completion(model="stabilityai/stablecode-completion-alpha-3b-4k", messages=messages, custom_llm_provider="huggingface")` | `os.environ['HF_TOKEN']`       |
+| [bigcode/starcoder](https://huggingface.co/bigcode/starcoder)                           | `completion(model="bigcode/starcoder", messages=messages, custom_llm_provider="huggingface")`          | `os.environ['HF_TOKEN']`       |
+| [google/flan-t5-xxl](https://huggingface.co/google/flan-t5-xxl)                         | `completion(model="google/flan-t5-xxl", messages=messages, custom_llm_provider="huggingface")`         | `os.environ['HF_TOKEN']`       |
+| [google/flan-t5-large](https://huggingface.co/google/flan-t5-large)                     | `completion(model="google/flan-t5-large", messages=messages, custom_llm_provider="huggingface")`       | `os.environ['HF_TOKEN']`       |
 
 ### OpenRouter Completion Models
 
diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
index 84bb43b8c..227d66ada 100644
Binary files a/litellm/__pycache__/__init__.cpython-311.pyc and b/litellm/__pycache__/__init__.cpython-311.pyc differ
diff --git a/litellm/__pycache__/main.cpython-311.pyc b/litellm/__pycache__/main.cpython-311.pyc
index 335839226..fd1970659 100644
Binary files a/litellm/__pycache__/main.cpython-311.pyc and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index 200ddc9d0..451db7357 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/main.py b/litellm/main.py
index dfd1d12c2..c047ee0c0 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -315,6 +315,8 @@ def completion(
       response = requests.post(API_URL, headers=headers, json=input_payload)
       ## LOGGING
       logging(model=model, input=prompt, custom_llm_provider=custom_llm_provider, additional_args={"max_tokens": max_tokens, "original_response": response.text}, logger_fn=logger_fn)
+      if isinstance(response, dict) and "error" in response:
+        raise Exception(response["error"])
       completion_response = response.json()[0]['generated_text']
       prompt_tokens = len(encoding.encode(prompt))
       completion_tokens = len(encoding.encode(completion_response))
diff --git a/pyproject.toml b/pyproject.toml
index 523e8d570..78e475ee3 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.386"
+version = "0.1.387"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"