Update app.py

app.py

@@ -8,7 +8,7 @@ from threading import Thread
 
 device = "auto"
 model_id = "ibm-granite/granite-3.0-8b-instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-3.0-8b-base")
 # drop device_map if running on CPU
 model = AutoModelForCausalLM.from_pretrained(model_id, device_map=device)
 model.eval()