tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "101": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "102": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "103": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30522": {
      "content": "<|im_end|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30523": {
      "content": "<|im_start|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|im_end|>",
    "<|im_start|>"
  ],
  "bos_token": "<|im_start|>",
  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": true,
  "eos_token": "<|im_end|>",
  "mask_token": "[MASK]",
  "model_max_length": 512,
  "never_split": null,
  "pad_token": "<|im_end|>",
  "sep_token": "[SEP]",
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "BertTokenizer",
  "unk_token": "[UNK]"
}