Step call func paused 10sec llama

app.py

@@ -10,7 +10,7 @@ os.environ['SAMBANOVA_API_KEY'] = os.getenv('sambanova_token')
 # Meta-Llama-3.1-405B-Instruct-8k
 # Create the model with explicit provider specification
 model = LiteLLMModel(
-    model_id="sambanova/Qwen2.5-72B-Instruct",  # Explicitly specify the sambanova provider
+    model_id="sambanova/Meta-Llama-3.1-70B-Instruct-8k",  # Explicitly specify the sambanova provider
     max_tokens=2096,
     temperature=0.5,
     api_base="https://api.sambanova.ai/v1",  # Specify the base URL for Sambanova, as in your working requests example