tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<sos>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<eos>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<cls>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "clean_up_tokenization_spaces": true,
  "cls_token": "<cls>",
  "eos_token": "<eos>",
  "mask_token": "<sos>",
  "max_length": 512,
  "model_max_length": 512,
  "pad_to_multiple_of": null,
  "pad_token": "<pad>",
  "pad_token_type_id": 0,
  "padding": "max_length",
  "padding_side": "right",
  "stride": 0,
  "tokenizer_class": "PreTrainedTokenizerFast",
  "truncation": true,
  "truncation_side": "right",
  "truncation_strategy": "longest_first"
}