Update app.py

app.py

@@ -3,7 +3,7 @@ from huggingface_hub import InferenceClient
 import gradio as gr
 import random
 
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 
 def respond(message, history):
    # responses = ["Yes", "No"]
@@ -20,9 +20,9 @@ def respond(message, history):
         messages.extend(history)
     
     response = client.chat_completion(
-        messages, max_tokens=100
+        messages, max_tokens=100, temperature=1.3, top_p=.76
     )
-
+    #temperature and top_p control randomness
 
     return response['choices'][0]['message']['content'].strip()