tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<|pad|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<|begin_of_text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<|end_of_text|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "<|eod|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "backend": "tokenizers",
  "bos_token": "<|begin_of_text|>",
  "clean_up_tokenization_spaces": false,
  "eod": "<|eod|>",
  "eos_token": "<|end_of_text|>",
  "extra_special_tokens": {
    "eod": "<|eod|>"
  },
  "model_max_length": 131072,
  "pad_token": "<|pad|>",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "unk_token": "<unk>"
}