Update app.py

app.py

@@ -30,7 +30,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 # Debugging: GPU check passed, loading model
 if torch.cuda.is_available():
-    model_id = "INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0"
+    model_id = "INSAIT-Institute/BgGPT-Gemma-2-9B-IT-v1.0"
     try:
         print("Loading model...")
         model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto", token=HF_TOKEN)