diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 8778aa3608..75d0ba55f3 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -964,14 +964,14 @@
         "mode": "completion"
     },
     "dolphin": {
-        "max_tokens": 4096,
+        "max_tokens": 16384,
         "input_cost_per_token": 0.0000005,
         "output_cost_per_token": 0.0000005,
         "litellm_provider": "nlp_cloud",
         "mode": "completion"
     },
     "chatdolphin": {
-        "max_tokens": 4096,
+        "max_tokens": 16384,
         "input_cost_per_token": 0.0000005,
         "output_cost_per_token": 0.0000005,
         "litellm_provider": "nlp_cloud",
diff --git a/litellm/tests/test_amazing_vertex_completion.py b/litellm/tests/test_amazing_vertex_completion.py
index 5e48d7941b..9b7473ea27 100644
--- a/litellm/tests/test_amazing_vertex_completion.py
+++ b/litellm/tests/test_amazing_vertex_completion.py
@@ -266,6 +266,8 @@ async def test_async_vertexai_streaming_response():
                 complete_response += chunk.choices[0].delta.content
             print(f"complete_response: {complete_response}")
             assert len(complete_response) > 0
+        except litellm.RateLimitError as e:
+            pass
         except litellm.Timeout as e:
             pass
         except Exception as e: