Update app.py

app.py

@@ -9,7 +9,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 
 DESCRIPTION = """\
 # Llama 3.2 1B Instruct Finetuned on 10% of Open Hermes Dataset
-This is a demo of [`diabolic6045/open-llama-Instruct`](https://huggingface.co/diabolic6045/open-llama-Instruct).
+This is a demo of [`diabolic6045/open-llama-3.2-1B-Instruct`](https://huggingface.co/diabolic6045/open-llama-3.2-1B-Instruct).
 """
 
 MAX_MAX_NEW_TOKENS = 1024
@@ -18,7 +18,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "1024"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "diabolic6045/open-llama-Instruct"
+model_id = "diabolic6045/open-llama-3.2-1B-Instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
@@ -127,7 +127,6 @@ chat_interface = gr.ChatInterface(
 
 with gr.Blocks(fill_height=True, theme=gr.themes.Ocean()) as demo:
     gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
     chat_interface.render()
 
 if __name__ == "__main__":