Deploy temporary working model: DialoGPT while awaiting Llama 3.1 access

app.py

@@ -62,8 +62,9 @@ async def load_model():
             
             logger.info("Loading model with transformers...")
             
-            # Use Llama 3.1 8B Instruct (requires HF token with access)
-            base_model_name = "meta-llama/Llama-3.1-8B-Instruct"
+            # Use a working model while waiting for Llama 3.1 access
+            # TODO: Change back to "meta-llama/Llama-3.1-8B-Instruct" once you have access
+            base_model_name = "microsoft/DialoGPT-medium"
             
             # Get HF token from environment
             hf_token = os.getenv("HF_TOKEN")