Update app.py

app.py

@@ -19,7 +19,7 @@ MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
-model_id = "google/gemma-1.1-2b-it"
+model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 
 # Load model with int8 quantization on CUDA (if available)
 if torch.cuda.is_available():