tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<pad>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [
    "<pad>",
    "<s>",
    "</s>",
    "<unk>"
  ],
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "</s>",
  "max_length": 20480,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
  "stride": 0,
  "tokenizer_class": "PreTrainedTokenizerFast",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<unk>"
}