Update app.py

app.py

@@ -230,7 +230,7 @@ logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
 # Load model and tokenizer
-model_name = "FreedomIntelligence/Apollo-2B"
+model_name = "FreedomIntelligence/Apollo-7B"
 # model_name = "emilyalsentzer/Bio_ClinicalBERT"
 # model_name = "FreedomIntelligence/Apollo-2B"
 
@@ -239,7 +239,6 @@ model = AutoModelForCausalLM.from_pretrained(model_name)
 
 tokenizer.pad_token = tokenizer.eos_token
 
-
 app = FastAPI(title="Apollo RAG Medical Chatbot")
 
 generation_config = GenerationConfig(
@@ -338,4 +337,4 @@ async def chat_fn(query: Query):
 
     except Exception as e:
         logger.error(f"Inference failed: {str(e)}")
-        raise HTTPException(status_code=500, detail="Model inference failed.")
+        raise HTTPException(status_code=500, detail="Model inference TimeOut failed.")