Update app.py

app.py

@@ -8,9 +8,9 @@ HF_TOKEN = os.environ.get("HF_TOKEN", None)
 
 # Load the tokenizer and model
 tokenizer = GemmaTokenizer.from_pretrained("google/codegemma-7b-it")
-model = AutoModelForCausalLM.from_pretrained("google/codegemma-7b-it", device_map="auto") #.to("cuda:0")
-
+model = AutoModelForCausalLM.from_pretrained("google/codegemma-7b-it", device_map="auto")
 
+@spaces.GPU(duration=120)
 def codegemma(message: str, history: list, temperature: float, max_new_tokens: int) -> str:
     """
     Generate a response using the CodeGemma model.
@@ -46,6 +46,7 @@ with gr.Blocks(fill_height=True) as demo:
     gr.ChatInterface(codegemma, 
                    examples=[["Write a Python function to calculate the nth fibonacci number."]], 
                    fill_height=True,
+                   placeholder=placeholder,
                    additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False, render=False),
                    additional_inputs=[
                        gr.Slider(0, 1, 0.95, label="Temperature", render=False),