tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "direction": "Right",
    "max_length": 512,
    "strategy": "LongestFirst",
    "stride": 0
  },
  "padding": {
    "strategy": {
      "Fixed": 512
    },
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 0,
    "pad_type_id": 0,
    "pad_token": "<pad>"
  },
  "added_tokens": [
    {
      "id": 0,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    },
    {
      "id": 1,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    },
    {
      "id": 2,
      "content": "<start>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    },
    {
      "id": 3,
      "content": "<end>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    },
    {
      "id": 4,
      "content": "<ecel>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 5,
      "content": "<fcel>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 6,
      "content": "<lcel>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 7,
      "content": "<ucel>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 8,
      "content": "<xcel>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 9,
      "content": "<nl>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 10,
      "content": "<ched>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 11,
      "content": "<rhed>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    },
    {
      "id": 12,
      "content": "<srow>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": false
    }
  ],
  "normalizer": null,
  "pre_tokenizer": null,
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordPiece",
    "unk_token": "[UNK]",
    "continuing_subword_prefix": "##",
    "max_input_chars_per_word": 100,
    "vocab": {}
  }
}