BART tokenizer adds two EOS (</s>) tokens?

Beginners
1

I have the problem that the BART tokenizer adds two tokens after the first segment.

tokenizer = BartTokenizer.from_pretrained("facebook/bart-base")
tokenizer.encode("What do you think?", "Nothing.", return_tensors="pt")

It outputs:

tensor([[    0,  2264,   109,    47,   206,   116,     2,     2, 19847,     4,
             2]])

Let’s decode again:

tokenizer.batch_decode(x)

['<s>What do you think?</s></s>Nothing.</s>']

Can I do anything about it?