Rename bytelevel

bytelevel/tokenizer.json

@@ -22,14 +22,7 @@
       "special": true
     }
   ],
-  "normalizer": {
-    "type": "Sequence",
-    "normalizers": [
-      {
-        "type": "NFD"
-      }
-    ]
-  },
+  "normalizer": null,
   "pre_tokenizer": {
     "type": "ByteLevel",
     "add_prefix_space": true,

bytelevel2/special_tokens_map.json

@@ -1,4 +0,0 @@
-{
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|padding|>"
-}

bytelevel2/tokenizer.json

@@ -1,315 +0,0 @@
-{
-  "version": "1.0",
-  "truncation": null,
-  "padding": null,
-  "added_tokens": [
-    {
-      "id": 0,
-      "content": "<|padding|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 1,
-      "content": "<|endoftext|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    }
-  ],
-  "normalizer": null,
-  "pre_tokenizer": {
-    "type": "ByteLevel",
-    "add_prefix_space": true,
-    "trim_offsets": true,
-    "use_regex": true
-  },
-  "post_processor": {
-    "type": "ByteLevel",
-    "add_prefix_space": true,
-    "trim_offsets": true,
-    "use_regex": true
-  },
-  "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": false,
-    "vocab": {
-      "<|padding|>": 0,
-      "<|endoftext|>": 1,
-      "!": 2,
-      "\"": 3,
-      "#": 4,
-      "$": 5,
-      "%": 6,
-      "&": 7,
-      "'": 8,
-      "(": 9,
-      ")": 10,
-      "*": 11,
-      "+": 12,
-      ",": 13,
-      "-": 14,
-      ".": 15,
-      "/": 16,
-      "0": 17,
-      "1": 18,
-      "2": 19,
-      "3": 20,
-      "4": 21,
-      "5": 22,
-      "6": 23,
-      "7": 24,
-      "8": 25,
-      "9": 26,
-      ":": 27,
-      ";": 28,
-      "<": 29,
-      "=": 30,
-      ">": 31,
-      "?": 32,
-      "@": 33,
-      "A": 34,
-      "B": 35,
-      "C": 36,
-      "D": 37,
-      "E": 38,
-      "F": 39,
-      "G": 40,
-      "H": 41,
-      "I": 42,
-      "J": 43,
-      "K": 44,
-      "L": 45,
-      "M": 46,
-      "N": 47,
-      "O": 48,
-      "P": 49,
-      "Q": 50,
-      "R": 51,
-      "S": 52,
-      "T": 53,
-      "U": 54,
-      "V": 55,
-      "W": 56,
-      "X": 57,
-      "Y": 58,
-      "Z": 59,
-      "[": 60,
-      "\\": 61,
-      "]": 62,
-      "^": 63,
-      "_": 64,
-      "`": 65,
-      "a": 66,
-      "b": 67,
-      "c": 68,
-      "d": 69,
-      "e": 70,
-      "f": 71,
-      "g": 72,
-      "h": 73,
-      "i": 74,
-      "j": 75,
-      "k": 76,
-      "l": 77,
-      "m": 78,
-      "n": 79,
-      "o": 80,
-      "p": 81,
-      "q": 82,
-      "r": 83,
-      "s": 84,
-      "t": 85,
-      "u": 86,
-      "v": 87,
-      "w": 88,
-      "x": 89,
-      "y": 90,
-      "z": 91,
-      "{": 92,
-      "|": 93,
-      "}": 94,
-      "~": 95,
-      "¡": 96,
-      "¢": 97,
-      "£": 98,
-      "¤": 99,
-      "¥": 100,
-      "¦": 101,
-      "§": 102,
-      "¨": 103,
-      "©": 104,
-      "ª": 105,
-      "«": 106,
-      "¬": 107,
-      "®": 108,
-      "¯": 109,
-      "°": 110,
-      "±": 111,
-      "²": 112,
-      "³": 113,
-      "´": 114,
-      "µ": 115,
-      "¶": 116,
-      "·": 117,
-      "¸": 118,
-      "¹": 119,
-      "º": 120,
-      "»": 121,
-      "¼": 122,
-      "½": 123,
-      "¾": 124,
-      "¿": 125,
-      "À": 126,
-      "Á": 127,
-      "Â": 128,
-      "Ã": 129,
-      "Ä": 130,
-      "Å": 131,
-      "Æ": 132,
-      "Ç": 133,
-      "È": 134,
-      "É": 135,
-      "Ê": 136,
-      "Ë": 137,
-      "Ì": 138,
-      "Í": 139,
-      "Î": 140,
-      "Ï": 141,
-      "Ð": 142,
-      "Ñ": 143,
-      "Ò": 144,
-      "Ó": 145,
-      "Ô": 146,
-      "Õ": 147,
-      "Ö": 148,
-      "×": 149,
-      "Ø": 150,
-      "Ù": 151,
-      "Ú": 152,
-      "Û": 153,
-      "Ü": 154,
-      "Ý": 155,
-      "Þ": 156,
-      "ß": 157,
-      "à": 158,
-      "á": 159,
-      "â": 160,
-      "ã": 161,
-      "ä": 162,
-      "å": 163,
-      "æ": 164,
-      "ç": 165,
-      "è": 166,
-      "é": 167,
-      "ê": 168,
-      "ë": 169,
-      "ì": 170,
-      "í": 171,
-      "î": 172,
-      "ï": 173,
-      "ð": 174,
-      "ñ": 175,
-      "ò": 176,
-      "ó": 177,
-      "ô": 178,
-      "õ": 179,
-      "ö": 180,
-      "÷": 181,
-      "ø": 182,
-      "ù": 183,
-      "ú": 184,
-      "û": 185,
-      "ü": 186,
-      "ý": 187,
-      "þ": 188,
-      "ÿ": 189,
-      "Ā": 190,
-      "ā": 191,
-      "Ă": 192,
-      "ă": 193,
-      "Ą": 194,
-      "ą": 195,
-      "Ć": 196,
-      "ć": 197,
-      "Ĉ": 198,
-      "ĉ": 199,
-      "Ċ": 200,
-      "ċ": 201,
-      "Č": 202,
-      "č": 203,
-      "Ď": 204,
-      "ď": 205,
-      "Đ": 206,
-      "đ": 207,
-      "Ē": 208,
-      "ē": 209,
-      "Ĕ": 210,
-      "ĕ": 211,
-      "Ė": 212,
-      "ė": 213,
-      "Ę": 214,
-      "ę": 215,
-      "Ě": 216,
-      "ě": 217,
-      "Ĝ": 218,
-      "ĝ": 219,
-      "Ğ": 220,
-      "ğ": 221,
-      "Ġ": 222,
-      "ġ": 223,
-      "Ģ": 224,
-      "ģ": 225,
-      "Ĥ": 226,
-      "ĥ": 227,
-      "Ħ": 228,
-      "��": 229,
-      "Ĩ": 230,
-      "ĩ": 231,
-      "Ī": 232,
-      "ī": 233,
-      "Ĭ": 234,
-      "ĭ": 235,
-      "Į": 236,
-      "į": 237,
-      "İ": 238,
-      "ı": 239,
-      "IJ": 240,
-      "ij": 241,
-      "Ĵ": 242,
-      "ĵ": 243,
-      "Ķ": 244,
-      "ķ": 245,
-      "ĸ": 246,
-      "Ĺ": 247,
-      "ĺ": 248,
-      "Ļ": 249,
-      "ļ": 250,
-      "Ľ": 251,
-      "ľ": 252,
-      "Ŀ": 253,
-      "ŀ": 254,
-      "Ł": 255,
-      "ł": 256,
-      "Ń": 257
-    },
-    "merges": []
-  }
-}

bytelevel2/tokenizer_config.json

@@ -1,29 +0,0 @@
-{
-  "add_prefix_space": true,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<|padding|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": null,
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|padding|>",
-  "tokenizer_class": "PreTrainedTokenizer",
-  "unk_token": null
-}