Update app.py

app.py

@@ -1,4 +1,5 @@
 import torch
+import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList
 
 tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-tuned-alpha-7b")
@@ -30,4 +31,19 @@ tokens = model.generate(
   do_sample=True,
   stopping_criteria=StoppingCriteriaList([StopOnTokens()])
 )
+with gr.Blocks() as demo:
+    
+    gr.Markdown("## StableLM-Tuned-Alpha-7b Chat")
+    gr.HTML('''<center><a href="https://huggingface.co/spaces/stabilityai/stablelm-tuned-alpha-chat?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>Duplicate the Space to skip the queue and run in a private space</center>''')
+    chatbot = gr.Chatbot().style(height=500)
+    with gr.Row():
+        with gr.Column(scale=0.70):
+            msg = gr.Textbox(label="Chat Message Box", placeholder="Chat Message Box", show_label=False).style(container=False)
+        with gr.Column(scale=0.30):
+          with gr.Row():
+              submit = gr.Button("Submit")
+              clear = gr.Button("Clear")    
+    system_msg = gr.Textbox(
+        start_message, label="System Message", interactive=False, visible=False)
+
 print(tokenizer.decode(tokens[0], skip_special_tokens=True))