tokenizer/special_tokens_map.json

{
  "bos_token": {
    "content": "<｜begin▁of▁sentence｜>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "content": "<｜end▁of▁sentence｜>",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "pad_token": "<｜end▁of▁sentence｜>"
}