Update app.py

app.py

@@ -1,12 +1,9 @@
+# app.py
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
 client = InferenceClient("joermd/speedy-llama2")
 
-
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -16,17 +13,13 @@ def respond(
     top_p,
 ):
     messages = [{"role": "system", "content": system_message}]
-
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
-
     messages.append({"role": "user", "content": message})
-
     response = ""
-
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,14 +28,9 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -59,6 +47,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()