Update app.py

app.py

@@ -23,7 +23,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "bartowski/gemma-2-9b-it-GGUF"
+model_id = "google/gemma-2-9b-it"
 tokenizer = GemmaTokenizerFast.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,