tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 13,
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 14,
      "content": "<|im_start|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 15,
      "content": "<|im_end|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "NFC"
  },
  "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}| ?[^\\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": false,
        "use_regex": false
      }
    ]
  },
  "post_processor": {
    "type": "ByteLevel",
    "add_prefix_space": false,
    "trim_offsets": false,
    "use_regex": false
  },
  "decoder": {
    "type": "ByteLevel",
    "add_prefix_space": false,
    "trim_offsets": false,
    "use_regex": false
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "0": 0,
      "1": 1,
      "2": 2,
      "3": 3,
      "4": 4,
      "5": 5,
      "6": 6,
      "7": 7,
      "8": 8,
      "9": 9,
      "Ċ": 10,
      "user": 11,
      "assistant": 12,
      "<|endoftext|>": 13,
      "<|im_start|>": 14,
      "<|im_end|>": 15
    },
    "unk_token": "<|endoftext|>"
  }
}