Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import random
 from huggingface_hub import InferenceClient
 
-client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
+client = InferenceClient("google/gemma-3-27b-it")
 # To change the LLM ^
 
 def respond(message, history):
@@ -14,7 +14,8 @@ def respond(message, history):
 
     messages.append({"role": "user", "content" : message})
     
-    response = client.chat_completion(messages, max_tokens = 100
+    response = client.chat_completion(messages, 
+        max_tokens = 100
      # to change the length  
     )