Update app.py

app.py

@@ -14,7 +14,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
 
 if torch.cuda.is_available():
-    model_id = "google/gemma-2-27b-it"
+    model_id = "google/gemma-2-9b-it"
     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="cuda")
     tokenizer = AutoTokenizer.from_pretrained(model_id)