How to separate multiturn dialog context in blenderbot?

Hello. I want to perform multiturn dialog with blenderbot model. I followed the documentation and here’s the code:

chat_history = []
uttr_sep = '</s> <s>'

    UTTR_input = input('User: ')
    UTTR = uttr_sep.join(chat_history)
    print('Input: ' + UTTR)

    inputs = tokenizer([UTTR], return_tensors='pt')
    reply_ids = model.generate(**inputs)
    REPLY = tokenizer.batch_decode(reply_ids, skip_special_tokens=True)[0]
    print("Bot:\n" + REPLY)


But model treats context as user’s input and sometimes </s> <s> shows in model’s responses.

In this issue, there are discussions about what to use to separate multiturns including </s> <s>, </sep>, \n, \t, but no conclusions.