Update app.py

app.py

@@ -42,7 +42,9 @@ if torch.cuda.is_available():
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False
 
-
+def make_prompt(entry):
+    return f"### Human: YOUR INSTRUCTION HERE: {entry} ### Assistant:"
+    
 @spaces.GPU
 def generate(
     message: str,
@@ -56,7 +58,7 @@ def generate(
     conversation = []
     for user, assistant in chat_history:
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
-    conversation.append({"role": "user", "content": message})
+    conversation.append({"role": "user", "content": make_prompt(message)})
 
     input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
@@ -99,7 +101,6 @@ chat_interface = gr.ChatInterface(
 
 with gr.Blocks(css="style.css") as demo:
     gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
     chat_interface.render()
     gr.Markdown(LICENSE)