Upload tokenizer

tokenizer.json

@@ -0,0 +1,325 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 256,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": "",
+    "end_of_word_suffix": "",
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "\u0000": 0,
+      "\u0001": 1,
+      "\u0002": 2,
+      "\u0003": 3,
+      "\u0004": 4,
+      "\u0005": 5,
+      "\u0006": 6,
+      "\u0007": 7,
+      "\b": 8,
+      "\t": 9,
+      "\n": 10,
+      "\u000b": 11,
+      "\f": 12,
+      "\r": 13,
+      "\u000e": 14,
+      "\u000f": 15,
+      "\u0010": 16,
+      "\u0011": 17,
+      "\u0012": 18,
+      "\u0013": 19,
+      "\u0014": 20,
+      "\u0015": 21,
+      "\u0016": 22,
+      "\u0017": 23,
+      "\u0018": 24,
+      "\u0019": 25,
+      "\u001a": 26,
+      "\u001b": 27,
+      "\u001c": 28,
+      "\u001d": 29,
+      "\u001e": 30,
+      "\u001f": 31,
+      " ": 32,
+      "!": 33,
+      "\"": 34,
+      "#": 35,
+      "$": 36,
+      "%": 37,
+      "&": 38,
+      "'": 39,
+      "(": 40,
+      ")": 41,
+      "*": 42,
+      "+": 43,
+      ",": 44,
+      "-": 45,
+      ".": 46,
+      "/": 47,
+      "0": 48,
+      "1": 49,
+      "2": 50,
+      "3": 51,
+      "4": 52,
+      "5": 53,
+      "6": 54,
+      "7": 55,
+      "8": 56,
+      "9": 57,
+      ":": 58,
+      ";": 59,
+      "<": 60,
+      "=": 61,
+      ">": 62,
+      "?": 63,
+      "@": 64,
+      "A": 65,
+      "B": 66,
+      "C": 67,
+      "D": 68,
+      "E": 69,
+      "F": 70,
+      "G": 71,
+      "H": 72,
+      "I": 73,
+      "J": 74,
+      "K": 75,
+      "L": 76,
+      "M": 77,
+      "N": 78,
+      "O": 79,
+      "P": 80,
+      "Q": 81,
+      "R": 82,
+      "S": 83,
+      "T": 84,
+      "U": 85,
+      "V": 86,
+      "W": 87,
+      "X": 88,
+      "Y": 89,
+      "Z": 90,
+      "[": 91,
+      "\\": 92,
+      "]": 93,
+      "^": 94,
+      "_": 95,
+      "`": 96,
+      "a": 97,
+      "b": 98,
+      "c": 99,
+      "d": 100,
+      "e": 101,
+      "f": 102,
+      "g": 103,
+      "h": 104,
+      "i": 105,
+      "j": 106,
+      "k": 107,
+      "l": 108,
+      "m": 109,
+      "n": 110,
+      "o": 111,
+      "p": 112,
+      "q": 113,
+      "r": 114,
+      "s": 115,
+      "t": 116,
+      "u": 117,
+      "v": 118,
+      "w": 119,
+      "x": 120,
+      "y": 121,
+      "z": 122,
+      "{": 123,
+      "|": 124,
+      "}": 125,
+      "~": 126,
+      "": 127,
+      "€": 128,
+      "": 129,
+      "‚": 130,
+      "ƒ": 131,
+      "„": 132,
+      "…": 133,
+      "†": 134,
+      "‡": 135,
+      "ˆ": 136,
+      "‰": 137,
+      "Š": 138,
+      "‹": 139,
+      "Œ": 140,
+      "": 141,
+      "Ž": 142,
+      "": 143,
+      "": 144,
+      "‘": 145,
+      "’": 146,
+      "“": 147,
+      "”": 148,
+      "•": 149,
+      "–": 150,
+      "—": 151,
+      "˜": 152,
+      "™": 153,
+      "š": 154,
+      "›": 155,
+      "œ": 156,
+      "": 157,
+      "ž": 158,
+      "Ÿ": 159,
+      " ": 160,
+      "¡": 161,
+      "¢": 162,
+      "£": 163,
+      "¤": 164,
+      "¥": 165,
+      "¦": 166,
+      "§": 167,
+      "¨": 168,
+      "©": 169,
+      "ª": 170,
+      "«": 171,
+      "¬": 172,
+      "­": 173,
+      "®": 174,
+      "¯": 175,
+      "°": 176,
+      "±": 177,
+      "²": 178,
+      "³": 179,
+      "´": 180,
+      "µ": 181,
+      "¶": 182,
+      "·": 183,
+      "¸": 184,
+      "¹": 185,
+      "º": 186,
+      "»": 187,
+      "¼": 188,
+      "½": 189,
+      "¾": 190,
+      "¿": 191,
+      "À": 192,
+      "Á": 193,
+      "Â": 194,
+      "Ã": 195,
+      "Ä": 196,
+      "Å": 197,
+      "Æ": 198,
+      "Ç": 199,
+      "È": 200,
+      "É": 201,
+      "Ê": 202,
+      "Ë": 203,
+      "Ì": 204,
+      "Í": 205,
+      "Î": 206,
+      "Ï": 207,
+      "Ð": 208,
+      "Ñ": 209,
+      "Ò": 210,
+      "Ó": 211,
+      "Ô": 212,
+      "Õ": 213,
+      "Ö": 214,
+      "×": 215,
+      "Ø": 216,
+      "Ù": 217,
+      "Ú": 218,
+      "Û": 219,
+      "Ü": 220,
+      "Ý": 221,
+      "Þ": 222,
+      "ß": 223,
+      "à": 224,
+      "á": 225,
+      "â": 226,
+      "ã": 227,
+      "ä": 228,
+      "å": 229,
+      "æ": 230,
+      "ç": 231,
+      "è": 232,
+      "é": 233,
+      "ê": 234,
+      "ë": 235,
+      "ì": 236,
+      "í": 237,
+      "î": 238,
+      "ï": 239,
+      "ð": 240,
+      "ñ": 241,
+      "ò": 242,
+      "ó": 243,
+      "ô": 244,
+      "õ": 245,
+      "ö": 246,
+      "÷": 247,
+      "ø": 248,
+      "ù": 249,
+      "ú": 250,
+      "û": 251,
+      "ü": 252,
+      "ý": 253,
+      "þ": 254,
+      "ÿ": 255,
+      "<|endoftext|>": 256
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 64,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}