{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 102,
"content": "",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 103,
"content": "",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 104,
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 105,
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 106,
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 107,
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 108,
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 109,
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 110,
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 111,
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 112,
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 113,
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 114,
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 115,
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 116,
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 117,
"content": "",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 118,
"content": "",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 119,
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 120,
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 121,
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 122,
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 123,
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 124,
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 125,
"content": "",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 126,
"content": "",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 127,
"content": "",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 128,
"content": "",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
{
"id": 1071,
"content": "<|sequence|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1072,
"content": "<|/sequence|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1073,
"content": "<|identity|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1074,
"content": "<|identity|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1075,
"content": "<|tail0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1076,
"content": "<|tail1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1077,
"content": "<|tail2|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1078,
"content": "<|tail3|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1079,
"content": "<|tail4|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1080,
"content": "<|head0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1081,
"content": "<|head1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1082,
"content": "<|head2|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1083,
"content": "<|head3|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1084,
"content": "<|head4|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1085,
"content": "<|chunk_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1086,
"content": "<|/chunk_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1087,
"content": "<|last_chunk_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
{
"id": 1088,
"content": "<|/last_chunk_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Prepend",
"prepend": "▁"
},
{
"type": "Replace",
"pattern": {
"String": " "
},
"content": "▁"
},
{
"type": "Replace",
"pattern": {
"String": " "
},
"content": "▁"
}
]
},
"pre_tokenizer": null,
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "",
"type_id": 1
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"": {
"id": "",
"ids": [
1
],
"tokens": [
""
]
}
}
},
"decoder": {
"type": "Sequence",
"decoders": [
{
"type": "Replace",
"pattern": {
"String": "▁"
},
"content": " "
},
{
"type": "ByteFallback"
},
{
"type": "Fuse"
},
{
"type": "Strip",
"content": " ",
"start": 1,
"stop": 0
}
]
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": true,
"byte_fallback": true,
"ignore_merges": false,
"vocab": {
"": 0,
"": 1,
"<|endoftext|>": 2,
"": 3,
"": 4,
"\n": 5,
"\t": 6,
"
": 7,
"
": 8,
"": 9,
"": 10,
"": 11,
"
": 12,
"": 13,
" | | ": 14,
"": 15,
"": 16,
"": 17,
"": 18,
"": 21,
"": 22,
"
": 23,
"": 24,
"": 25,
"": 26,
"": 27,
"": 28,
"": 29,
"": 30,
"": 31,
"": 32,
"
": 33,
"
": 34,
"
": 35,
"": 36,
"": 37,
"": 38,
"
": 39,
"": 40,
"": 41,
"
": 42,
"": 43,
"
": 44,
"
": 45,
"": 46,
"": 47,
"
": 48,
"": 49,
"": 50,
"": 51,
"0": 52,
"1": 53,
"2": 54,
"3": 55,
"4": 56,
"5": 57,
"6": 58,
"7": 59,
"8": 60,
"9": 61,
"+": 62,
"-": 63,
"=": 64,
",": 65,
"。": 66,
"!": 67,
"?": 68,
"、": 69,
":": 70,
"¥": 71,
".": 72,
"!": 73,
"?": 74,
"...": 75,
"。。。": 76,
"。。。。。。": 77,
"《": 78,
"》": 79,
"【": 80,
"】": 81,
"『": 82,
"』": 83,
"```": 84,
"": 86,
"---": 87,
"": 88,
";": 89,
".": 90,
"=": 91,
"<": 92,
">": 93,
"-": 94,
"+": 95,
"%": 96,
"‼": 97,
"㊣": 98,
"/": 99,
"|": 100,
"": 101,
"": 102,
"": 103,
"<|im_start|>": 104,
"<|im_end|>": 105,
"<|object_ref_start|>": 106,
"<|object_ref_end|>": 107,
"<|box_start|>": 108,
"<|box_end|>": 109,
"<|quad_start|>": 110,
"<|quad_end|>": 111,
"<|vision_start|>": 112,
"<|vision_end|>": 113,
"<|vision_pad|>": 114,
"<|image_pad|>": 115,
"<|video_pad|>": 116,
"": 117,
"": 118,
"<|fim_prefix|>": 119,
"<|fim_middle|>": 120,
"<|fim_suffix|>": 121,
"<|fim_pad|>": 122,
"<|repo_name|>": 123,
"<|file_sep|>": 124,
"": 125,
"": 126,
"": 127,
"": 128,
"": 129,
"": 130,
"": 131,
"": 132,
"": 133,
"": 134,
"": 135,
"": 136,
"": 137,
"": 138,
"": 139,
"": 140,
"": 141,
"": 142,
"": 143,
"": 144,
"": 145,
"": 146,
"": 147,
"": 148,
"": 149,
"": 150,
"": 151,
"": 152,
"": 153,
"": 154,
"": 155,
"": 156,
"": 157,
"": 158,
"": 159,
"": 160,
"": 161,
"": 162,
"": 163,
"": 164,
"": 165,
"": 166,
"": 167,
"": 168,
"": 169,
"": 170,
"": 171,
"": 172,
"": 173,
"": 174,
"": 175,
"": 176,
"": 177,
"": 178,
"": 179,
"": 180,
"": 181,
"": 182,
"": 183,
"": 184,
"": 185,
"": 186,
"": 187,
"": 188,
"": 189,
"": 190,
"": 191,
"": 192,
"": 193,
"": 194,
"": 195,
"": 196,
"": 197,
"": 198,
"": 199,
"": 200,
"": 201,
"": 202,
"": 203,
"": 204,
"": 205,
"": 206,
"": 207,
"": 208,
"": 209,
"": 210,
"": 211,
"": 212,
"": 213,
"": 214,
"": 215,
"": 216,
"": 217,
"": 218,
"": 219,
"": 220,
"": 221,
"": 222,
"": 223,
"": 224,
"": 225,
"": 226,
"": 227,
"": 228,
"": 229,
"": 230,
"": 231,
"": 232,
"": 233,
"": 234,
"": 235,
"": 236,
"": 237,
"": 238,
"": 239,
"": 240,
"": 241,
"": 242,
"": 243,
"": 244,
"": 245,
"": 246,
"": 247,
"": 248,
"": 249,
"": 250,
"": 251,
"": 252,
"": 253,
"": 254,
"": 255,
"": 256,
"": 257,
"": 258,
"": 259,
"": 260,
"": 261,
"": 262,
"": 263,
"": 264,
"": 265,
"": 266,
"": 267,
"": 268,
"": 269,
"": 270,
"": 271,
"": 272,
"": 273,
"": 274,
"": 275,
"": 276,
"": 277,
"": 278,
"": 279,
"": 280,
"": 281,
"": 282,
"": 283,
"": 284,
"": 285,
"": 286,
"": 287,
"": 288,
"": 289,
"": 290,
"": 291,
"": 292,
"": 293,
"": 294,
"": 295,
"": 296,
"": 297,
"": 298,
"": 299,
"": 300,
"": 301,
"": 302,
"": 303,
"": 304,
"": 305,
"": 306,
"": 307,
"": 308,
"": 309,
"": 310,
"": 311,
"": 312,
"": 313,
"": 314,
"": 315,
"": 316,
"": 317,
"": 318,
"": 319,
"": 320,
"": 321,
"": 322,
"": 323,
"": 324,
"": 325,
"": 326,
"": 327,
"": 328,
"": 329,
"": 330,
"": 331,
"": 332,
"": 333,
"": 334,
"": 335,
"": 336,
"": 337,
"": 338,
"": 339,
"": 340,
"": 341,
"": 342,
"": 343,
"": 344,
"": 345,
"": 346,
"": 347,
"": 348,
"": 349,
"": 350,
"": 351,
"": 352,
"": 353,
"": 354,
"": 355,
"": 356,
"": 357,
"": 358,
"": 359,
"": 360,
"": 361,
"": 362,
"": 363,
"": 364,
"": 365,
"": 366,
"": 367,
"": 368,
"": 369,
"": 370,
"": 371,
"": 372,
"": 373,
"": 374,
"": 375,
"": 376,
"": 377,
"": 378,
"