Update app.py

app.py

@@ -5,18 +5,16 @@ client = InferenceClient(
     "mistralai/Mixtral-8x7B-Instruct-v0.1"
 )
 
-
 def format_prompt(message, history):
-    system = "<|system|>\nYou are a helpful virtual assistant that answer user's question with easy to understand words.</s>\n"
-    prompt = ""
-    for user_prompt, bot_response in history:
-        prompt += f"<|user|>\n{user_prompt}</s>\n"
-        prompt += f"<|assistant|>\n{bot_response}</s>\n"
-    prompt += f"<|user|>\n{message}</s>\n"
-    return prompt
+  prompt = "<s>"
+  for user_prompt, bot_response in history:
+    prompt += f"[INST] {user_prompt} [/INST]"
+    prompt += f" {bot_response}</s> "
+  prompt += f"[INST] {message} [/INST]"
+  return prompt
 
 def generate(
-    prompt, history, temperature=0.9, max_new_tokens=500, top_p=0.95, repetition_penalty=1.0,
+    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -82,21 +80,10 @@ additional_inputs=[
     )
 ]
 
-css = """
-  #mkd {
-    height: 500px; 
-    overflow: auto; 
-    border: 1px solid #ccc; 
-  }
-"""
-
-with gr.Blocks(css=css) as inf:
-    gr.HTML("<h1><center>zephyr-7b-alpha<h1><center>")
-    gr.HTML("<h3><center>In this demo, you can chat with <a href='https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha'>zephyr-7b-alpha</a> model. 💬<h3><center>")
-    gr.ChatInterface(
-        generate,
-        additional_inputs=additional_inputs,
-        examples=[["Can squirrel swims?"], ["Write a poem about squirrel."]]
-    )
 
-inf.queue().launch()
+gr.ChatInterface(
+    fn=generate,
+    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
+    additional_inputs=additional_inputs,
+    title="Mixtral 46.7B"
+).launch(show_api=True)