Update app.py

app.py

@@ -21,8 +21,8 @@ app = FastAPI()
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-# Load the Google Gemma 2B model and tokenizer
-model_id = "google/gemma-2b"  # Use Google Gemma 2B
+# Load a smaller model (GPT-Neo-125M) and tokenizer
+model_id = "EleutherAI/gpt-neo-125M"  # Use GPT-Neo-125M for faster performance
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 # Load the model without quantization for CPU