Update app.py

app.py

@@ -30,6 +30,7 @@ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
 #model_id = "nltpt/Llama-3.2-3B-Instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id,token = access_token)
+tokenizer.pad_token = tokenizer.eos_token
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",