tokenizer_config.json

{
  "add_bos_token": true,
  "add_eos_token": false,
  "unk_token": "<unk>",
  "bos_token": "<s>",
  "eos_token": "</s>",
  "pad_token": "<pad|LLM-jp>",
  "cls_token": "<CLS|LLM-jp>",
  "sep_token": "<SEP|LLM-jp>",
  "eod_token": "<EOD|LLM-jp>",
  "mask_token": "<mask|LLM-jp>",
  "extra_ids": 0,
  "additional_special_tokens": [
    "<s>",
    "</s>"
  ],
  "sp_model_kwargs": {},
  "model_max_length": 1000000000000000019884624838656,
  "clean_up_tokenization_spaces": false,
  "special_tokens_map_file": null,
  "tokenizer_class": "PreTrainedTokenizerFast"
}