raised max_tokens, lowered temperature

app.py

@@ -16,9 +16,9 @@ def respond(message, history):
 
     for message in client.chat_completion(
         model="meta-llama/Llama-3.1-8B-Instruct",
-        temperature=0.8,
+        temperature=0.4,
         messages=messages,
-        max_tokens=150,
+        max_tokens=350,
         stream=True
     ):
         token = message.choices[0].delta.content