tokenizer_config.json

{
  "added_tokens_decoder": {
    "-1": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "0": {
      "content": "<|unk|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<|bos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|eos|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<|bos|>",
  "clean_up_tokenization_spaces": false,
  "do_lower_case": false,
  "eos_token": "<|eos|>",
  "extra_special_tokens": {},
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<|pad|>",
  "tokenizer_class": "BltTokenizerHF",
  "unk_token": "<|unk|>",
  "vocab": {
    "<|bos|>": 2,
    "<|eos|>": 3,
    "<|pad|>": 0,
    "<|unk|>": 1,
    "hello": 4,
    "world": 5,
    "ประเทศไทย": 7,
    "สวัสดี": 6
  }
}