Update app.py

app.py

@@ -4,7 +4,7 @@ import gradio as gr
 import random
 
 
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 
 
 def respond(message, history):
@@ -21,7 +21,8 @@ def respond(message, history):
         messages.extend(history)
     
     response = client.chat_completion(
-        messages, max_tokens = 100
+        messages, max_tokens = 100, temprature=1.3, top_p=.2
+        #temp and top_p control randomness
     )
     return response['choices'][0]['message']['content'].strip()