test and work

app/main.py

@@ -178,7 +178,7 @@ def get_llm(model_name: str):
     elif model_name == "Llama":
         logging.info("Initializing Llama model - note this is a gated model and requires special access")
         try:
-            # Try smaller Llama model that's under the 10GB limit
+            # Try smaller Llama model that's under the 10GB limit push
             return HFInferenceLLM(
                 model="meta-llama/Llama-3.2-3B-Instruct",
                 provider="hf-inference",