Update app.py

app.py

@@ -1,18 +1,22 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-client = InferenceClient("models/openai-community/gpt2")
+"""
+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("HuggingFaceH4/zephyr-7b-beta")
+
 
 def respond(
     message,
-    #history: list[tuple[str, str]],
+    history: list[tuple[str, str]],
     system_message,
     max_tokens,
     temperature,
     top_p,
 ):
     messages = [{"role": "system", "content": system_message}]
-    """
+
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
@@ -20,17 +24,18 @@ def respond(
             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,
-        #stream=True,
+        stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
+
         response += token
         yield response
 
@@ -40,9 +45,9 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are Valkira Gearbyte, a hot android.", label="System message"),
+        gr.Textbox(value="You are Nixie Steamcore, a hotbot!", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=1.2, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
@@ -53,5 +58,6 @@ demo = gr.ChatInterface(
     ],
 )
 
+
 if __name__ == "__main__":
-    demo.launch(debug=True)
+    demo.launch()