Update app.py

app.py

@@ -12,7 +12,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 model = model.to("cpu")
 
-pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=512)
+pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=128)
 
 def generate_response(prompt):
     clear_memory()