BDCoderAI-600m / tokenizer.json
Jamil82's picture
Upload folder using huggingface_hub
7c5837c verified
Raw
History Blame Contribute Delete
10.2 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<|pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<|bos|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "<|eos|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "<|unk|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 4,
"content": "<|system|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 5,
"content": "<|user|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 6,
"content": "<|assistant|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 7,
"content": "<|plan|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 8,
"content": "<|tool_call|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 9,
"content": "<|tool_result|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 10,
"content": "<|code|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 11,
"content": "<|/code|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 12,
"content": "<|file|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 13,
"content": "<|diff|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 14,
"content": "<|error|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 15,
"content": "<|fix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 16,
"content": "<|python|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 17,
"content": "<|javascript|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 18,
"content": "<|typescript|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 19,
"content": "<|cpp|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 20,
"content": "<|java|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 21,
"content": "<|go|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 22,
"content": "<|rust|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 23,
"content": "<|end_tool|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "NFC"
},
"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": "<|unk|>",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"<|pad|>": 0,
"<|bos|>": 1,
"<|eos|>": 2,
"<|unk|>": 3,
"<|system|>": 4,
"<|user|>": 5,
"<|assistant|>": 6,
"<|plan|>": 7,
"<|tool_call|>": 8,
"<|tool_result|>": 9,
"<|code|>": 10,
"<|/code|>": 11,
"<|file|>": 12,
"<|diff|>": 13,
"<|error|>": 14,
"<|fix|>": 15,
"<|python|>": 16,
"<|javascript|>": 17,
"<|typescript|>": 18,
"<|cpp|>": 19,
"<|java|>": 20,
"<|go|>": 21,
"<|rust|>": 22,
"<|end_tool|>": 23,
"!": 24,
"\"": 25,
"#": 26,
"$": 27,
"%": 28,
"&": 29,
"'": 30,
"(": 31,
")": 32,
"*": 33,
"+": 34,
",": 35,
"-": 36,
".": 37,
"/": 38,
"0": 39,
"1": 40,
"2": 41,
"3": 42,
"4": 43,
"5": 44,
"6": 45,
"7": 46,
"8": 47,
"9": 48,
":": 49,
";": 50,
"<": 51,
"=": 52,
">": 53,
"?": 54,
"@": 55,
"A": 56,
"B": 57,
"C": 58,
"D": 59,
"E": 60,
"F": 61,
"G": 62,
"H": 63,
"I": 64,
"J": 65,
"K": 66,
"L": 67,
"M": 68,
"N": 69,
"O": 70,
"P": 71,
"Q": 72,
"R": 73,
"S": 74,
"T": 75,
"U": 76,
"V": 77,
"W": 78,
"X": 79,
"Y": 80,
"Z": 81,
"[": 82,
"\\": 83,
"]": 84,
"^": 85,
"_": 86,
"`": 87,
"a": 88,
"b": 89,
"c": 90,
"d": 91,
"e": 92,
"f": 93,
"g": 94,
"h": 95,
"i": 96,
"j": 97,
"k": 98,
"l": 99,
"m": 100,
"n": 101,
"o": 102,
"p": 103,
"q": 104,
"r": 105,
"s": 106,
"t": 107,
"u": 108,
"v": 109,
"w": 110,
"x": 111,
"y": 112,
"z": 113,
"{": 114,
"|": 115,
"}": 116,
"~": 117,
"¡": 118,
"¢": 119,
"£": 120,
"¤": 121,
"¥": 122,
"¦": 123,
"§": 124,
"¨": 125,
"©": 126,
"ª": 127,
"«": 128,
"¬": 129,
"®": 130,
"¯": 131,
"°": 132,
"±": 133,
"²": 134,
"³": 135,
"´": 136,
"µ": 137,
"¶": 138,
"·": 139,
"¸": 140,
"¹": 141,
"º": 142,
"»": 143,
"¼": 144,
"½": 145,
"¾": 146,
"¿": 147,
"À": 148,
"Á": 149,
"Â": 150,
"Ã": 151,
"Ä": 152,
"Å": 153,
"Æ": 154,
"Ç": 155,
"È": 156,
"É": 157,
"Ê": 158,
"Ë": 159,
"Ì": 160,
"Í": 161,
"Î": 162,
"Ï": 163,
"Ð": 164,
"Ñ": 165,
"Ò": 166,
"Ó": 167,
"Ô": 168,
"Õ": 169,
"Ö": 170,
"×": 171,
"Ø": 172,
"Ù": 173,
"Ú": 174,
"Û": 175,
"Ü": 176,
"Ý": 177,
"Þ": 178,
"ß": 179,
"à": 180,
"á": 181,
"â": 182,
"ã": 183,
"ä": 184,
"å": 185,
"æ": 186,
"ç": 187,
"è": 188,
"é": 189,
"ê": 190,
"ë": 191,
"ì": 192,
"í": 193,
"î": 194,
"ï": 195,
"ð": 196,
"ñ": 197,
"ò": 198,
"ó": 199,
"ô": 200,
"õ": 201,
"ö": 202,
"÷": 203,
"ø": 204,
"ù": 205,
"ú": 206,
"û": 207,
"ü": 208,
"ý": 209,
"þ": 210,
"ÿ": 211,
"Ā": 212,
"ā": 213,
"Ă": 214,
"ă": 215,
"Ą": 216,
"ą": 217,
"Ć": 218,
"ć": 219,
"Ĉ": 220,
"ĉ": 221,
"Ċ": 222,
"ċ": 223,
"Č": 224,
"č": 225,
"Ď": 226,
"ď": 227,
"Đ": 228,
"đ": 229,
"Ē": 230,
"ē": 231,
"Ĕ": 232,
"ĕ": 233,
"Ė": 234,
"ė": 235,
"Ę": 236,
"ę": 237,
"Ě": 238,
"ě": 239,
"Ĝ": 240,
"ĝ": 241,
"Ğ": 242,
"ğ": 243,
"Ġ": 244,
"ġ": 245,
"Ģ": 246,
"ģ": 247,
"Ĥ": 248,
"ĥ": 249,
"Ħ": 250,
"ħ": 251,
"Ĩ": 252,
"ĩ": 253,
"Ī": 254,
"ī": 255,
"Ĭ": 256,
"ĭ": 257,
"Į": 258,
"į": 259,
"İ": 260,
"ı": 261,
"IJ": 262,
"ij": 263,
"Ĵ": 264,
"ĵ": 265,
"Ķ": 266,
"ķ": 267,
"ĸ": 268,
"Ĺ": 269,
"ĺ": 270,
"Ļ": 271,
"ļ": 272,
"Ľ": 273,
"ľ": 274,
"Ŀ": 275,
"ŀ": 276,
"Ł": 277,
"ł": 278,
"Ń": 279
},
"merges": []
}
}