Update app.py

app.py

@@ -21,7 +21,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "2048"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "nltpt/Llama-3.2-3B-Instruct" # "giustinod/TestLogica-AZService"
+model_id = "giustinod/TestLogica-AZService"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
@@ -130,7 +130,6 @@ chat_interface = gr.ChatInterface(
 
 with gr.Blocks(css="style.css", fill_height=True) as demo:
     gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
     chat_interface.render()
 
 if __name__ == "__main__":