tokenizer_config.json

{
  "add_bos_token": false,
  "add_eos_token": false,
  "added_tokens_decoder": {
    "0": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "64000": {
      "content": "<|CLS|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64001": {
      "content": "<|SEP|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64002": {
      "content": "<|EOD|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64003": {
      "content": "<|MASK|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "64004": {
      "content": "<|PAD|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<|CLS|>",
    "<|SEP|>",
    "<|EOD|>",
    "<|MASK|>",
    "<|PAD|>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_neo.NEOTokenizer",
      null
    ]
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "eos_token": "</s>",
  "extra_special_tokens": {},
  "model_max_length": 4096,
  "pad_token": "<unk>",
  "padding_side": "right",
  "sp_model_kwargs": {},
  "split_special_tokens": false,
  "tokenizer_class": "NEOTokenizer",
  "unk_token": "<unk>",
  "use_fast": false
}