Update app.py

app.py

@@ -9,7 +9,7 @@ import gradio as gr
 
 text_generator = None
 is_hugging_face = True
-model_id = "google/gemma-2-9b-it"# too big
+model_id = "AXCXEPT/EZO-Common-9B-gemma-2-it"# too big
 #model_id = "google/gemma-2-2b-it"
 huggingface_token = os.getenv("HUGGINGFACE_TOKEN")
 device = "auto" # torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -56,7 +56,7 @@ if not is_hugging_face:
 
 print("initialized")
 
-#@spaces.GPU(duration=60)
+@spaces.GPU(duration=60)
 def generate_text(messages):
     if is_hugging_face:#need everytime initialize for ZeroGPU
         model = AutoModelForCausalLM.from_pretrained(