diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
index 6c515ddae..566a5c21d 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 a9e7a2174..eede7b903 100644
Binary files a/litellm/__pycache__/main.cpython-311.pyc and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/__pycache__/timeout.cpython-311.pyc b/litellm/__pycache__/timeout.cpython-311.pyc
index 68f0223aa..aa097515c 100644
Binary files a/litellm/__pycache__/timeout.cpython-311.pyc and b/litellm/__pycache__/timeout.cpython-311.pyc differ
diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index 538c69758..47392379d 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/llms/replicate.py b/litellm/llms/replicate.py
index 5dff48d08..03b688020 100644
--- a/litellm/llms/replicate.py
+++ b/litellm/llms/replicate.py
@@ -14,7 +14,7 @@ class ReplicateError(Exception):
         )  # Call the base class constructor with the parameters it needs
 
 # Function to start a prediction and get the prediction URL
-def start_prediction(version_id, input_data, api_token):
+def start_prediction(version_id, input_data, api_token, logging_obj):
     base_url = "https://api.replicate.com/v1"
     headers = {
         "Authorization": f"Token {api_token}",
@@ -27,12 +27,19 @@ def start_prediction(version_id, input_data, api_token):
         "max_new_tokens": 500,
     }
 
+        ## LOGGING
+    logging_obj.pre_call(
+            input=input_data["prompt"],
+            api_key="",
+            additional_args={"complete_input_dict": initial_prediction_data, "headers": headers},
+    )
+
     response = requests.post(f"{base_url}/predictions", json=initial_prediction_data, headers=headers)
     if response.status_code == 201:
         response_data = response.json()
         return response_data.get("urls", {}).get("get")
     else:
-        raise ReplicateError(response.status_code, "Failed to start prediction.")
+        raise ReplicateError(response.status_code, message=response.text)
 
 # Function to handle prediction response (non-streaming)
 def handle_prediction_response(prediction_url, api_token, print_verbose):
@@ -111,18 +118,12 @@ def completion(
         **optional_params
     }
 
-    ## LOGGING
-    logging_obj.pre_call(
-            input=prompt,
-            api_key="",
-            additional_args={"complete_input_dict": input_data},
-    )
     ## COMPLETION CALL
     ## Replicate Compeltion calls have 2 steps
     ## Step1: Start Prediction: gets a prediction url
     ## Step2: Poll prediction url for response
     ## Step2: is handled with and without streaming
-    prediction_url = start_prediction(version_id, input_data, api_key)
+    prediction_url = start_prediction(version_id, input_data, api_key, logging_obj=logging_obj)
     print_verbose(prediction_url)
 
     # Handle the prediction response (streaming or non-streaming)
diff --git a/litellm/tests/test_model_alias_map.py b/litellm/tests/test_model_alias_map.py
index 29f14cdf3..2bdbfdb6f 100644
--- a/litellm/tests/test_model_alias_map.py
+++ b/litellm/tests/test_model_alias_map.py
@@ -18,13 +18,15 @@ model_alias_map = {
 
 litellm.model_alias_map = model_alias_map
 
-print(
+try:
     completion(
         "llama2",
         messages=[{"role": "user", "content": "Hey, how's it going?"}],
         top_p=0.1,
-        temperature=0,
+        temperature=0.1,
         num_beams=4,
         max_tokens=60,
     )
-)
+except Exception as e:
+    print(e.status_code)
+    print(e)
diff --git a/pyproject.toml b/pyproject.toml
index 8265d9bc5..e714248b6 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.541"
+version = "0.1.542"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"