Upload 2 files

inference.py

@@ -31,7 +31,7 @@ except ImportError:
 # Defaults are set only for API_BASE_URL and MODEL_NAME 
 # (and should reflect your active inference setup):
 API_BASE_URL = os.getenv("API_BASE_URL", "https://router.huggingface.co/v1")
-MODEL_NAME = os.getenv("MODEL_NAME", "meta-llama/Llama-3.3-70B-Instruct")
+MODEL_NAME = os.getenv("MODEL_NAME", "llama-3.3-70b-versatile")
 HF_TOKEN = os.getenv("HF_TOKEN")
 LOCAL_IMAGE_NAME = os.getenv("LOCAL_IMAGE_NAME")