From b81af3ae57559b61dc2e85cbc7c53d01f944b071 Mon Sep 17 00:00:00 2001
From: Jose Javier <26491792+josejg@users.noreply.github.com>
Date: Sun, 18 Aug 2024 16:52:36 -0700
Subject: [PATCH] Correct error message for inference wrapper (#1459)

---
 llmfoundry/models/inference_api_wrapper/openai_causal_lm.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/llmfoundry/models/inference_api_wrapper/openai_causal_lm.py b/llmfoundry/models/inference_api_wrapper/openai_causal_lm.py
index 8253134bcd..4f1f2e6f04 100644
--- a/llmfoundry/models/inference_api_wrapper/openai_causal_lm.py
+++ b/llmfoundry/models/inference_api_wrapper/openai_causal_lm.py
@@ -102,7 +102,7 @@ def try_generate_completion(self, prompt: str, num_tokens: int):
                 break
             except RateLimitError as e:
                 if 'You exceeded your current quota' in str(
-                    e._message,
+                    e.message,
                 ):  # pyright: ignore
                     raise e
                 delay *= 2 * (1 + random.random())