Update app.py

app.py

@@ -17,6 +17,7 @@ fourbit_models = [
     "unsloth/gemma-7b-bnb-4bit",             # Gemma 2.2x faster!
 ] # More models at https://huggingface.co/unsloth
 
+model = FastLanguageModel(device="cpu")
 model, tokenizer = FastLanguageModel.from_pretrained(
     model_name = "danishmuhammad/ccat2025_llama_gguf",
     max_seq_length = max_seq_length,