tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "max_length": 2048,
    "direction": "Right",
    "stride": 0
  },
  "padding": {
    "strategy": "fixed_size",
    "direction": "Right",
    "pad_to_multiple_of": 8,
    "pad_id": 2,
    "pad_type_id": 0,
    "pad_token": "</s>"
  },
  "added_tokens": [
    {
      "id": 0,
      "special": true,
      "content": "<unk>",
      "single_word": false
    },
    {
      "id": 1,
      "special": true,
      "content": "<s>",
      "single_word": false
    },
    {
      "id": 2,
      "special": true,
      "content": "</s>",
      "single_word": false
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Precompiled",
        "precompiled_charsmap": "",
        "lstrip": false,
        "rstrip": false
      }
    ]
  },
  "pre_tokenizer": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      "$A",
      "</s>"
    ],
    "pair": [
      "$A",
      "</s>",
      "$B",
      "</s>"
    ],
    "special_tokens": {
      "</s>": {
        "id": 2,
        "ids": [
          2
        ],
        "tokens": [
          "</s>"
        ]
      }
    }
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "<unk>",
    "continuing_subword_prefix": "",
    "end_of_word_suffix": "",
    "fuse_unk": false,
    "vocab": {
      "<unk>": 0,
      "<s>": 1,
      "</s>": 2
    }
  }
}