DivCenterer / tokenizer.json
thenukegun10x's picture
Upload DivCenterer v5 1.1M model
9b994a0 verified
Raw History Blame Contribute Delete
17.7 kB
{ "format": "divcenterer-constrained-byte-bpe-v1", "base_vocab_size": 256, "special_tokens": [ "<|user|>", "<|assistant|>", "<|end|>" ], "merges": [ [ 32, 32 ], [ 10, 259 ], [ 110, 116 ], [ 58, 32 ], [ 105, 110 ], [ 100, 105 ], [ 98, 111 ], [ 101, 261 ], [ 104, 101 ], [ 115, 116 ], [ 100, 121 ], [ 103, 101 ], [ 60, 47 ], [ 265, 269 ], [ 101, 114 ], [ 264, 118 ], [ 105, 100 ], [ 108, 97 ], [ 97, 270 ], [ 266, 273 ], [ 268, 277 ], [ 108, 101 ], [ 97, 114 ], [ 105, 116 ], [ 99, 278 ], [ 10, 10 ], [ 34, 62 ], [ 61, 34 ], [ 272, 62 ], [ 116, 267 ], [ 111, 110 ], [ 105, 103 ], [ 112, 276 ], [ 262, 283 ], [ 292, 59 ], [ 116, 105 ], [ 67, 83 ], [ 295, 83 ], [ 60, 274 ], [ 271, 274 ], [ 297, 32 ], [ 298, 62 ], [ 48, 48 ], [ 282, 101 ], [ 72, 84 ], [ 77, 76 ], [ 303, 304 ], [ 104, 116 ], [ 290, 306 ], [ 263, 45 ], [ 97, 108 ], [ 267, 307 ], [ 109, 281 ], [ 286, 279 ], [ 108, 121 ], [ 114, 275 ], [ 103, 263 ], [ 49, 301 ], [ 45, 302 ], [ 48, 59 ], [ 60, 287 ], [ 99, 276 ], [ 104, 59 ], [ 109, 115 ], [ 109, 308 ], [ 115, 115 ], [ 115, 291 ], [ 118, 321 ], [ 121, 262 ], [ 260, 259 ], [ 262, 316 ], [ 262, 318 ], [ 264, 325 ], [ 271, 287 ], [ 280, 120 ], [ 299, 275 ], [ 310, 329 ], [ 311, 315 ], [ 312, 285 ], [ 317, 322 ], [ 320, 324 ], [ 323, 335 ], [ 331, 327 ], [ 336, 330 ], [ 338, 293 ], [ 339, 337 ], [ 340, 326 ], [ 111, 114 ], [ 97, 110 ], [ 115, 101 ], [ 111, 261 ], [ 334, 286 ], [ 45, 49 ], [ 45, 48 ], [ 32, 344 ], [ 99, 349 ], [ 105, 101 ], [ 294, 99 ], [ 109, 97 ], [ 294, 289 ], [ 289, 313 ], [ 265, 120 ], [ 354, 266 ], [ 263, 103 ], [ 99, 358 ], [ 101, 116 ], [ 119, 282 ], [ 365, 104 ], [ 117, 115 ], [ 117, 268 ], [ 347, 100 ], [ 116, 104 ], [ 290, 110 ], [ 309, 371 ], [ 112, 346 ], [ 118, 355 ], [ 119, 373 ], [ 374, 375 ], [ 376, 116 ], [ 106, 368 ], [ 117, 116 ], [ 281, 356 ], [ 380, 280 ], [ 348, 363 ], [ 45, 361 ], [ 70, 333 ], [ 71, 314 ], [ 99, 101 ], [ 102, 121 ], [ 102, 333 ], [ 103, 314 ], [ 105, 387 ], [ 291, 386 ], [ 341, 388 ], [ 341, 389 ], [ 372, 343 ], [ 378, 390 ], [ 383, 293 ], [ 384, 360 ], [ 391, 343 ], [ 392, 59 ], [ 393, 59 ], [ 395, 396 ], [ 357, 263 ], [ 270, 116 ], [ 114, 111 ], [ 105, 115 ], [ 367, 362 ], [ 309, 313 ], [ 117, 112 ], [ 117, 114 ], [ 114, 101 ], [ 97, 116 ], [ 364, 409 ], [ 412, 110 ], [ 104, 346 ], [ 116, 281 ], [ 415, 403 ], [ 101, 108 ], [ 118, 273 ], [ 60, 381 ], [ 271, 381 ], [ 419, 353 ], [ 420, 62 ], [ 60, 382 ], [ 271, 382 ], [ 423, 353 ], [ 424, 62 ], [ 85, 348 ], [ 105, 122 ], [ 299, 344 ], [ 60, 402 ], [ 271, 402 ], [ 430, 353 ], [ 431, 62 ], [ 107, 101 ], [ 282, 115 ], [ 101, 100 ], [ 67, 278 ], [ 111, 102 ], [ 99, 116 ], [ 101, 280 ], [ 101, 110 ], [ 114, 413 ], [ 108, 108 ], [ 265, 370 ], [ 121, 280 ], [ 112, 347 ], [ 349, 407 ], [ 356, 407 ], [ 414, 428 ], [ 418, 448 ], [ 449, 447 ], [ 112, 379 ], [ 84, 267 ], [ 112, 281 ], [ 454, 266 ], [ 105, 118 ], [ 109, 266 ], [ 440, 457 ], [ 446, 417 ], [ 111, 99 ], [ 97, 434 ], [ 116, 111 ], [ 119, 275 ], [ 463, 403 ], [ 97, 348 ], [ 280, 465 ], [ 99, 281 ], [ 467, 100 ], [ 268, 445 ], [ 108, 355 ], [ 112, 470 ], [ 115, 408 ], [ 471, 100 ], [ 472, 473 ], [ 114, 302 ], [ 110, 111 ], [ 370, 411 ], [ 97, 112 ], [ 82, 413 ], [ 109, 275 ], [ 379, 452 ], [ 115, 111 ], [ 111, 119 ], [ 115, 99 ], [ 354, 404 ], [ 485, 108 ], [ 99, 414 ], [ 347, 487 ], [ 410, 441 ], [ 49, 55 ], [ 98, 106 ], [ 101, 439 ], [ 111, 491 ], [ 493, 492 ], [ 357, 308 ], [ 102, 460 ], [ 370, 362 ], [ 496, 367 ], [ 49, 56 ], [ 49, 54 ], [ 49, 50 ], [ 49, 57 ], [ 267, 404 ], [ 49, 51 ], [ 49, 52 ], [ 48, 51 ], [ 48, 52 ], [ 49, 53 ], [ 377, 45 ], [ 110, 101 ], [ 111, 117 ], [ 48, 50 ], [ 48, 54 ], [ 77, 461 ], [ 469, 115 ], [ 366, 263 ], [ 264, 410 ], [ 351, 50 ], [ 363, 115 ], [ 517, 519 ], [ 80, 379 ], [ 275, 101 ], [ 476, 116 ], [ 484, 489 ], [ 351, 55 ], [ 80, 466 ], [ 87, 475 ], [ 283, 115 ], [ 107, 408 ], [ 311, 529 ], [ 48, 56 ], [ 48, 55 ], [ 71, 456 ], [ 100, 280 ], [ 480, 534 ], [ 533, 101 ], [ 45, 301 ], [ 283, 436 ], [ 79, 481 ], [ 102, 105 ], [ 112, 404 ], [ 540, 443 ], [ 541, 118 ], [ 351, 51 ], [ 351, 57 ], [ 49, 285 ], [ 352, 55 ], [ 48, 285 ], [ 53, 285 ], [ 351, 56 ], [ 352, 53 ], [ 48, 57 ], [ 351, 52 ], [ 352, 52 ], [ 352, 54 ], [ 352, 56 ], [ 352, 50 ], [ 351, 54 ], [ 352, 51 ], [ 101, 112 ], [ 351, 53 ], [ 52, 285 ], [ 352, 57 ], [ 478, 112 ], [ 54, 285 ], [ 48, 53 ], [ 50, 285 ], [ 55, 285 ], [ 108, 117 ], [ 99, 408 ], [ 100, 100 ], [ 102, 117 ], [ 51, 285 ], [ 56, 285 ], [ 97, 439 ], [ 57, 285 ], [ 108, 100 ], [ 350, 459 ], [ 113, 117 ], [ 114, 405 ], [ 334, 312 ], [ 350, 464 ], [ 350, 486 ], [ 350, 488 ], [ 109, 111 ], [ 350, 494 ], [ 99, 111 ], [ 350, 416 ], [ 350, 458 ], [ 350, 495 ], [ 350, 361 ], [ 350, 497 ], [ 350, 498 ], [ 99, 461 ], [ 97, 268 ], [ 350, 283 ], [ 350, 360 ], [ 350, 468 ], [ 105, 99 ], [ 350, 503 ], [ 99, 108 ], [ 601, 511 ], [ 112, 466 ], [ 509, 310 ], [ 115, 522 ], [ 263, 605 ], [ 75, 101 ], [ 103, 456 ], [ 117, 309 ], [ 118, 405 ], [ 607, 560 ], [ 608, 441 ], [ 610, 609 ], [ 83, 364 ], [ 97, 115 ], [ 102, 346 ], [ 115, 428 ], [ 283, 362 ], [ 509, 617 ], [ 619, 436 ], [ 68, 111 ], [ 98, 404 ], [ 100, 483 ], [ 111, 481 ], [ 115, 273 ], [ 119, 263 ], [ 119, 475 ], [ 119, 625 ], [ 410, 627 ], [ 622, 628 ], [ 626, 623 ], [ 267, 364 ], [ 515, 632 ], [ 105, 261 ], [ 111, 634 ], [ 112, 289 ], [ 112, 635 ], [ 115, 636 ], [ 410, 638 ], [ 480, 637 ], [ 639, 100 ], [ 101, 281 ], [ 357, 434 ], [ 564, 642 ], [ 73, 116 ], [ 97, 120 ], [ 97, 121 ], [ 101, 115 ], [ 109, 101 ], [ 117, 348 ], [ 119, 647 ], [ 543, 522 ], [ 645, 115 ], [ 646, 648 ], [ 651, 115 ], [ 99, 104 ], [ 105, 112 ], [ 110, 657 ], [ 112, 364 ], [ 112, 411 ], [ 115, 658 ], [ 289, 101 ], [ 370, 405 ], [ 660, 656 ], [ 661, 659 ], [ 65, 571 ], [ 97, 100 ], [ 97, 105 ], [ 97, 118 ], [ 98, 280 ], [ 98, 417 ], [ 100, 101 ], [ 112, 277 ], [ 114, 117 ], [ 115, 119 ], [ 276, 670 ], [ 280, 115 ], [ 347, 675 ], [ 668, 676 ], [ 669, 679 ], [ 671, 483 ], [ 672, 667 ], [ 674, 677 ], [ 678, 273 ], [ 83, 116 ], [ 98, 121 ], [ 101, 120 ], [ 104, 511 ], [ 115, 435 ], [ 115, 688 ], [ 460, 570 ], [ 685, 445 ], [ 687, 575 ], [ 690, 577 ], [ 691, 121 ], [ 510, 436 ], [ 45, 310 ], [ 105, 109 ], [ 109, 263 ], [ 275, 436 ], [ 443, 697 ], [ 482, 569 ], [ 542, 362 ], [ 543, 700 ], [ 572, 701 ], [ 698, 309 ], [ 699, 706 ], [ 702, 358 ], [ 45, 50 ], [ 49, 49 ], [ 265, 116 ], [ 404, 711 ], [ 101, 478 ], [ 111, 116 ], [ 115, 438 ], [ 116, 713 ], [ 355, 116 ], [ 579, 717 ], [ 715, 116 ], [ 716, 714 ], [ 98, 282 ], [ 101, 277 ], [ 110, 281 ], [ 346, 721 ], [ 569, 723 ], [ 722, 114 ], [ 97, 109 ], [ 98, 273 ], [ 104, 111 ], [ 112, 580 ], [ 114, 478 ], [ 346, 347 ], [ 443, 483 ], [ 727, 728 ], [ 729, 733 ], [ 730, 109 ], [ 731, 275 ], [ 732, 270 ], [ 97, 103 ], [ 98, 314 ], [ 98, 368 ], [ 100, 114 ], [ 105, 114 ], [ 108, 302 ], [ 109, 364 ], [ 111, 370 ], [ 115, 309 ], [ 115, 411 ], [ 115, 579 ], [ 115, 585 ], [ 116, 121 ], [ 404, 741 ], [ 410, 108 ], [ 417, 744 ], [ 587, 745 ], [ 739, 289 ], [ 740, 270 ], [ 742, 756 ], [ 743, 753 ], [ 747, 751 ], [ 748, 754 ], [ 749, 759 ], [ 750, 746 ], [ 98, 379 ], [ 98, 580 ], [ 99, 280 ], [ 103, 266 ] ], "vocab_size": 768, "requested_vocab_size": 768, "min_pair_frequency": 2, "atomizer": "syntax-aware-html-css-segments-v1", "merge_policy": "BPE merges stay within prose lexemes, whitespace runs, complete HTML tags, or recognized CSS declarations.", "training_rows": 3276, "training_note": "Trained on the train split only; merges cannot cross pretokenized HTML/CSS atoms." }
{
"format": "divcenterer-constrained-byte-bpe-v1",
"base_vocab_size": 256,
"special_tokens": [
"<|user|>",
"<|assistant|>",
"<|end|>"
],
"merges": [
[
32,
32
],
[
10,
259
],
[
110,
116
],
[
58,
32
],
[
105,
110
],
[
100,
105
],
[
98,
111
],
[
101,
261
],
[
104,
101
],
[
115,
116
],
[
100,
121
],
[
103,
101
],
[
60,
47
],
[
265,
269
],
[
101,
114
],
[
264,
118
],
[
105,
100
],
[
108,
97
],
[
97,
270
],
[
266,
273
],
[
268,
277
],
[
108,
101
],
[
97,
114