app.py

import gradio as gr
import random as rd
from huggingface_hub import InferenceClient

client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
def respond (message, history):
   messages = [{"role": "system", "content": "You are a chatbot who is sassy and doesnt explain an anser unless someone asks twice."}]
   if history:
      messages.extend(history)
   messages.append({"role": "user", "content": message})
   response = “”
   for message in client.chat_completion(
        messages,
        max_tokens=500,
        temperature=0.2,
        top_p=0.9,
        stream=True
    ):
        token = message.choices[0].delta.content
        response += token
   yield response['choices'][0]['message']['content'].strip()
    
    
chatbot = gr.ChatInterface(respond, type = "messages")
chatbot.launch(debug=True)