diff --git a/.gitignore b/.gitignore
index 50085bd29..abc4ecb0c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -52,5 +52,3 @@ litellm/proxy/_new_secret_config.yaml
 litellm/proxy/_new_secret_config.yaml
 litellm/proxy/_super_secret_config.yaml
 litellm/proxy/_super_secret_config.yaml
-.python-version
-litellm/llms/tokenizers/9b5ad71b2ce5302211f9c61530b329a4922fc6a4
diff --git a/litellm/main.py b/litellm/main.py
index a284cd440..59d98580c 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -2165,7 +2165,7 @@ def completion(
             """
             assume input to custom LLM api bases follow this format:
             resp = requests.post(
-                api_base,
+                api_base, 
                 json={
                     'model': 'meta-llama/Llama-2-13b-hf', # model name
                     'params': {
@@ -2302,7 +2302,6 @@ def batch_completion(
     deployment_id=None,
     request_timeout: Optional[int] = None,
     timeout: Optional[int] = 600,
-    return_exceptions: bool = False,
     # Optional liteLLM function params
     **kwargs,
 ):
@@ -2326,7 +2325,6 @@ def batch_completion(
         user (str, optional): The user string for generating completions. Defaults to "".
         deployment_id (optional): The deployment ID for generating completions. Defaults to None.
         request_timeout (int, optional): The request timeout for generating completions. Defaults to None.
-        return_exceptions (bool): Whether to return exceptions and partial results when exceptions occur. Defaults to False.
 
     Returns:
         list: A list of completion results.
@@ -2385,17 +2383,7 @@ def batch_completion(
                     completions.append(future)
 
         # Retrieve the results from the futures
-        # results = [future.result() for future in completions]
-        if return_exceptions:
-            results = []
-            for future in completions:
-                try:
-                    results.append(future.result())
-                except Exception as exc:
-                    results.append(exc)
-        else:
-            results = [future.result() for future in completions]
-
+        results = [future.result() for future in completions]
     return results
 
 
diff --git a/litellm/tests/test_batch_completion_return_exceptions.py b/litellm/tests/test_batch_completion_return_exceptions.py
deleted file mode 100644
index b44146993..000000000
--- a/litellm/tests/test_batch_completion_return_exceptions.py
+++ /dev/null
@@ -1,29 +0,0 @@
-"""Test batch_completion's return_exceptions."""
-import pytest
-import litellm
-
-msg1 = [{"role": "user", "content": "hi 1"}]
-msg2 = [{"role": "user", "content": "hi 2"}]
-
-
-def test_batch_completion_return_exceptions_default():
-    """Test batch_completion's return_exceptions."""
-    with pytest.raises(Exception):
-        _ = litellm.batch_completion(
-            model="gpt-3.5-turbo",
-            messages=[msg1, msg2],
-            api_key="sk_xxx",  # deliberately set invalid key
-            # return_exceptions=False,
-        )
-
-
-def test_batch_completion_return_exceptions_true():
-    """Test batch_completion's return_exceptions."""
-    res = litellm.batch_completion(
-        model="gpt-3.5-turbo",
-        messages=[msg1, msg2],
-        api_key="sk_xxx",  # deliberately set invalid key
-        return_exceptions=True,
-    )
-
-    assert isinstance(res[0], litellm.exceptions.AuthenticationError)