tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 128000,
      "content": "<|begin_of_text|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128001,
      "content": "<|end_of_text|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128002,
      "content": "<|reserved_special_token_0|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128003,
      "content": "<|reserved_special_token_1|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128004,
      "content": "<|reserved_special_token_2|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128005,
      "content": "<|reserved_special_token_3|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128006,
      "content": "<|start_header_id|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128007,
      "content": "<|end_header_id|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128008,
      "content": "<|reserved_special_token_4|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128009,
      "content": "<|eot_id|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 128010,
      "content": "<|reserved_special_token_5|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Sequence",
    "pretokenizers": [
      {
        "type": "Split",
        "pattern": {
          "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
        },
        "behavior": "Isolated",
        "invert": false
      },
      {
        "type": "ByteLevel",
        "add_prefix_space": false,
        "trim_offsets": true,
        "use_regex": false
      }
    ]
  },
  "post_processor": {
    "type": "Sequence",
    "processors": [
      {
        "type": "ByteLevel",
        "add_prefix_space": true,
        "trim_offsets": false,
        "use_regex": true
      },
      {
        "type": "TemplateProcessing",
        "single": [
          {
            "SpecialToken": {
              "id": "<|begin_of_text|>",
              "type_id": 0
            }
          },
          {
            "Sequence": {
              "id": "A",
              "type_id": 0
            }
          }
        ],
        "pair": [
          {
            "SpecialToken": {
              "id": "<|begin_of_text|>",
              "type_id": 0
            }
          },
          {
            "Sequence": {
              "id": "A",
              "type_id": 0
            }
          },
          {
            "SpecialToken": {
              "id": "<|begin_of_text|>",
              "type_id": 1
            }
          },
          {
            "Sequence": {
              "id": "B",
              "type_id": 1
            }
          }
        ],
        "special_tokens": {
          "<|begin_of_text|>": {
            "id": "<|begin_of_text|>",
            "ids": [
              128000
            ],
            "tokens": [
              "<|begin_of_text|>"
            ]
          }
        }
      }
    ]
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": true,
    "trim_offsets": true,
    "use_regex": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": true,
    "vocab": {},
    "merges": []
  }
}