Update app.py

app.py

@@ -5,7 +5,7 @@ import random
 
 
 # Making requests to the model to generate responses:
-client = InferenceClient('HuggingFaceH4/zephyr-7b-beta') 
+client = InferenceClient('Qwen/Qwen2.5-72B-Instruct') 
 
 
 def respond(message, history):
@@ -18,8 +18,9 @@ def respond(message, history):
     if history:
         messages.extend(history)
       
-    response = client.chat_completion(messages, max_tokens=100)
-
+    response = client.chat_completion(messages, max_tokens=100, temperature=1.7, top_p=.3)
+    # Temp and top_p control randomness
+    
     return response['choices'][0]['message']['content'].strip()