fix: max new tokens

app.py

@@ -20,7 +20,7 @@ def respond(
     input_text = "<|tasktype|>\n" + task_type.strip()
     input_text += "\n<|context|>\n" + message.strip() + "\n<|task|>\n"
 
-    response = client.text_generation(input_text, max_length=max_tokens, temperature=temperature, top_p=top_p)
+    response = client.text_generation(input_text, max_new_tokens=max_tokens, temperature=temperature, top_p=top_p)
 
     return response
     # messages = []