add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<": 255, ">": 254, "#": 256}

merges.txt

@@ -0,0 +1 @@
+#version: 0.2 - Trained by `huggingface/tokenizers`

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": ">", "eos_token": "<", "unk_token": "<|endoftext|>", "pad_token": "#"}

tokenizer.json

@@ -0,0 +1,324 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 254,
+      "content": ">",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 255,
+      "content": "<",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 256,
+      "content": "#",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true
+  },
+  "post_processor": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": false
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": "",
+    "end_of_word_suffix": "",
+    "fuse_unk": false,
+    "vocab": {
+      "<|endoftext|>": 0,
+      "\n": 1,
+      " ": 2,
+      "!": 3,
+      "&": 4,
+      "'": 5,
+      "(": 6,
+      ")": 7,
+      "*": 8,
+      "+": 9,
+      "-": 10,
+      ".": 11,
+      "/": 12,
+      "0": 13,
+      "1": 14,
+      "2": 15,
+      "3": 16,
+      "4": 17,
+      "5": 18,
+      "6": 19,
+      "7": 20,
+      "8": 21,
+      "9": 22,
+      ":": 23,
+      ";": 24,
+      "@": 25,
+      "A": 26,
+      "B": 27,
+      "C": 28,
+      "D": 29,
+      "E": 30,
+      "F": 31,
+      "G": 32,
+      "H": 33,
+      "I": 34,
+      "J": 35,
+      "K": 36,
+      "L": 37,
+      "M": 38,
+      "N": 39,
+      "O": 40,
+      "P": 41,
+      "Q": 42,
+      "R": 43,
+      "S": 44,
+      "T": 45,
+      "U": 46,
+      "V": 47,
+      "W": 48,
+      "X": 49,
+      "Y": 50,
+      "Z": 51,
+      "a": 52,
+      "b": 53,
+      "c": 54,
+      "d": 55,
+      "e": 56,
+      "f": 57,
+      "g": 58,
+      "h": 59,
+      "i": 60,
+      "j": 61,
+      "k": 62,
+      "l": 63,
+      "m": 64,
+      "n": 65,
+      "o": 66,
+      "p": 67,
+      "q": 68,
+      "r": 69,
+      "s": 70,
+      "t": 71,
+      "u": 72,
+      "v": 73,
+      "w": 74,
+      "x": 75,
+      "y": 76,
+      "z": 77,
+      "¡": 78,
+      "¢": 79,
+      "£": 80,
+      "¤": 81,
+      "¥": 82,
+      "¦": 83,
+      "§": 84,
+      "¨": 85,
+      "©": 86,
+      "ª": 87,
+      "«": 88,
+      "¬": 89,
+      "®": 90,
+      "¯": 91,
+      "°": 92,
+      "±": 93,
+      "²": 94,
+      "³": 95,
+      "´": 96,
+      "µ": 97,
+      "¶": 98,
+      "·": 99,
+      "¸": 100,
+      "¹": 101,
+      "º": 102,
+      "»": 103,
+      "¼": 104,
+      "½": 105,
+      "¾": 106,
+      "¿": 107,
+      "Á": 108,
+      "Â": 109,
+      "Ã": 110,
+      "Ä": 111,
+      "Å": 112,
+      "Æ": 113,
+      "Ç": 114,
+      "È": 115,
+      "É": 116,
+      "Ê": 117,
+      "Ì": 118,
+      "Í": 119,
+      "Î": 120,
+      "Ï": 121,
+      "Ð": 122,
+      "Ô": 123,
+      "Ö": 124,
+      "×": 125,
+      "Ü": 126,
+      "ß": 127,
+      "à": 128,
+      "á": 129,
+      "â": 130,
+      "ã": 131,
+      "ä": 132,
+      "å": 133,
+      "æ": 134,
+      "ç": 135,
+      "è": 136,
+      "é": 137,
+      "ê": 138,
+      "ë": 139,
+      "ì": 140,
+      "í": 141,
+      "î": 142,
+      "ï": 143,
+      "ñ": 144,
+      "ò": 145,
+      "ó": 146,
+      "ô": 147,
+      "õ": 148,
+      "ö": 149,
+      "ø": 150,
+      "ù": 151,
+      "ú": 152,
+      "û": 153,
+      "ü": 154,
+      "ý": 155,
+      "ÿ": 156,
+      "ā": 157,
+      "ć": 158,
+      "č": 159,
+      "Ğ": 160,
+      "ğ": 161,
+      "Ġ": 162,
+      "Ģ": 163,
+      "ģ": 164,
+      "Ĥ": 165,
+      "ĥ": 166,
+      "Ĩ": 167,
+      "ĩ": 168,
+      "Ī": 169,
+      "ī": 170,
+      "Ĭ": 171,
+      "ĭ": 172,
+      "į": 173,
+      "İ": 174,
+      "ı": 175,
+      "IJ": 176,
+      "ij": 177,
+      "Ĵ": 178,
+      "ĵ": 179,
+      "Ķ": 180,
+      "ĸ": 181,
+      "Ĺ": 182,
+      "ĺ": 183,
+      "Ļ": 184,
+      "ļ": 185,
+      "Ľ": 186,
+      "ľ": 187,
+      "Ŀ": 188,
+      "ŀ": 189,
+      "Ł": 190,
+      "ł": 191,
+      "Ń": 192,
+      "ŋ": 193,
+      "ō": 194,
+      "Œ": 195,
+      "œ": 196,
+      "Ś": 197,
+      "ŝ": 198,
+      "Ş": 199,
+      "ş": 200,
+      "š": 201,
+      "ū": 202,
+      "ŵ": 203,
+      "ź": 204,
+      "Ž": 205,
+      "ž": 206,
+      "ǘ": 207,
+      "ȝ": 208,
+      "ɑ": 209,
+      "ɔ": 210,
+      "ə": 211,
+      "ɛ": 212,
+      "ɡ": 213,
+      "ɣ": 214,
+      "ɥ": 215,
+      "ɨ": 216,
+      "ɩ": 217,
+      "ɲ": 218,
+      "ʁ": 219,
+      "ʃ": 220,
+      "ʋ": 221,
+      "ʒ": 222,
+      "ʔ": 223,
+      "ʻ": 224,
+      "ʼ": 225,
+      "ʾ": 226,
+      "ʿ": 227,
+      "́": 228,
+      "̃": 229,
+      "̐": 230,
+      "̓": 231,
+      "͠": 232,
+      "Δ": 233,
+      "α": 234,
+      "β": 235,
+      "μ": 236,
+      "σ": 237,
+      "а": 238,
+      "е": 239,
+      "ḷ": 240,
+      "ṃ": 241,
+      "ṇ": 242,
+      "ṣ": 243,
+      "ṭ": 244,
+      "–": 245,
+      "‘": 246,
+      "’": 247,
+      "′": 248,
+      "‿": 249,
+      "₂": 250,
+      "€": 251,
+      "−": 252,
+      "∴": 253
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": ">", "eos_token": "<", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "./", "pad_token": "#", "tokenizer_class": "GPT2Tokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"<|endoftext|>":0,"\n":1," ":2,"!":3,"&":4,"'":5,"(":6,")":7,"*":8,"+":9,"-":10,".":11,"/":12,"0":13,"1":14,"2":15,"3":16,"4":17,"5":18,"6":19,"7":20,"8":21,"9":22,":":23,";":24,"@":25,"A":26,"B":27,"C":28,"D":29,"E":30,"F":31,"G":32,"H":33,"I":34,"J":35,"K":36,"L":37,"M":38,"N":39,"O":40,"P":41,"Q":42,"R":43,"S":44,"T":45,"U":46,"V":47,"W":48,"X":49,"Y":50,"Z":51,"a":52,"b":53,"c":54,"d":55,"e":56,"f":57,"g":58,"h":59,"i":60,"j":61,"k":62,"l":63,"m":64,"n":65,"o":66,"p":67,"q":68,"r":69,"s":70,"t":71,"u":72,"v":73,"w":74,"x":75,"y":76,"z":77,"¡":78,"¢":79,"£":80,"¤":81,"¥":82,"¦":83,"§":84,"¨":85,"©":86,"ª":87,"«":88,"¬":89,"®":90,"¯":91,"°":92,"±":93,"²":94,"³":95,"´":96,"µ":97,"¶":98,"·":99,"¸":100,"¹":101,"º":102,"»":103,"¼":104,"½":105,"¾":106,"¿":107,"Á":108,"Â":109,"Ã":110,"Ä":111,"Å":112,"Æ":113,"Ç":114,"È":115,"É":116,"Ê":117,"Ì":118,"Í":119,"Î":120,"Ï":121,"Ð":122,"Ô":123,"Ö":124,"×":125,"Ü":126,"ß":127,"à":128,"á":129,"â":130,"ã":131,"ä":132,"å":133,"æ":134,"ç":135,"è":136,"é":137,"ê":138,"ë":139,"ì":140,"í":141,"î":142,"ï":143,"ñ":144,"ò":145,"ó":146,"ô":147,"õ":148,"ö":149,"ø":150,"ù":151,"ú":152,"û":153,"ü":154,"ý":155,"ÿ":156,"ā":157,"ć":158,"č":159,"Ğ":160,"ğ":161,"Ġ":162,"Ģ":163,"ģ":164,"Ĥ":165,"ĥ":166,"Ĩ":167,"ĩ":168,"Ī":169,"ī":170,"Ĭ":171,"ĭ":172,"į":173,"İ":174,"ı":175,"IJ":176,"ij":177,"Ĵ":178,"ĵ":179,"Ķ":180,"ĸ":181,"Ĺ":182,"ĺ":183,"Ļ":184,"ļ":185,"Ľ":186,"ľ":187,"Ŀ":188,"ŀ":189,"Ł":190,"ł":191,"Ń":192,"ŋ":193,"ō":194,"Œ":195,"œ":196,"Ś":197,"ŝ":198,"Ş":199,"ş":200,"š":201,"ū":202,"ŵ":203,"ź":204,"Ž":205,"ž":206,"ǘ":207,"ȝ":208,"ɑ":209,"ɔ":210,"ə":211,"ɛ":212,"ɡ":213,"ɣ":214,"ɥ":215,"ɨ":216,"ɩ":217,"ɲ":218,"ʁ":219,"ʃ":220,"ʋ":221,"ʒ":222,"ʔ":223,"ʻ":224,"ʼ":225,"ʾ":226,"ʿ":227,"́":228,"̃":229,"̐":230,"̓":231,"͠":232,"Δ":233,"α":234,"β":235,"μ":236,"σ":237,"а":238,"е":239,"ḷ":240,"ṃ":241,"ṇ":242,"ṣ":243,"ṭ":244,"–":245,"‘":246,"’":247,"′":248,"‿":249,"₂":250,"€":251,"−":252,"∴":253}