{ "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": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "Sequence", "normalizers": [ { "type": "NFC" } ] }, "pre_tokenizer": { "type": "ByteLevel", "add_prefix_space": false, "trim_offsets": true, "use_regex": true }, "post_processor": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": false, "use_regex": true }, "decoder": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": false, "use_regex": true }, "model": { "type": "BPE", "dropout": null, "unk_token": "", "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": true, "vocab": { "": 0, "": 1, "": 2, "": 3, " ": 4, "a": 5, "b": 6, "c": 7, "d": 8, "e": 9, "f": 10, "g": 11, "h": 12, "i": 13, "j": 14, "k": 15, "l": 16, "m": 17, "n": 18, "o": 19, "p": 20, "q": 21, "r": 22, "s": 23, "t": 24, "u": 25, "v": 26, "w": 27, "x": 28, "y": 29, "z": 30, "A": 31, "B": 32, "C": 33, "D": 34, "E": 35, "F": 36, "G": 37, "H": 38, "I": 39, "J": 40, "K": 41, "L": 42, "M": 43, "N": 44, "O": 45, "P": 46, "Q": 47, "R": 48, "S": 49, "T": 50, "U": 51, "V": 52, "W": 53, "X": 54, "Y": 55, "Z": 56, "0": 57, "1": 58, "2": 59, "3": 60, "4": 61, "5": 62, "6": 63, "7": 64, "8": 65, "9": 66, ".": 67, ",": 68, ";": 69, ":": 70, "!": 71, "?": 72, "'": 73, "-": 74, "\"": 75, "(": 76, ")": 77, "[": 78, "]": 79, "{": 80, "}": 81, "/": 82, "@": 83, "#": 84, "$": 85, "%": 86, "&": 87, "*": 88, "+": 89, "=": 90, "_": 91, "~": 92, "<": 93, ">": 94, "|": 95, "`": 96, "\\": 97, "\n": 98, "\t": 99, "\r": 100, "—": 101, "–": 102, "…": 103, ") # left double quote\nadd(": 104, "°": 105, "අ": 106, "ආ": 107, "ඇ": 108, "ඈ": 109, "ඉ": 110, "ඊ": 111, "උ": 112, "ඌ": 113, "ඍ": 114, "ඎ": 115, "එ": 116, "ඒ": 117, "ඓ": 118, "ඔ": 119, "ඕ": 120, "ඖ": 121, "ක": 122, "ඛ": 123, "ග": 124, "ඝ": 125, "ඞ": 126, "ච": 127, "ඡ": 128, "ජ": 129, "ඣ": 130, "ඤ": 131, "ට": 132, "ඨ": 133, "ඩ": 134, "ඪ": 135, "ණ": 136, "ත": 137, "ථ": 138, "ද": 139, "ධ": 140, "න": 141, "ප": 142, "ඵ": 143, "බ": 144, "භ": 145, "ම": 146, "ය": 147, "ර": 148, "ල": 149, "ව": 150, "ශ": 151, "ෂ": 152, "ස": 153, "හ": 154, "ළ": 155, "ෆ": 156, "ා": 157, "ැ": 158, "ෑ": 159, "ි": 160, "ී": 161, "ු": 162, "ූ": 163, "ෘ": 164, "ෙ": 165, "ේ": 166, "ෛ": 167, "ො": 168, "ෝ": 169, "ෞ": 170, "්": 171, "ං": 172, "ඃ": 173, "ඁ": 174, "ෲ": 175, "ෳ": 176, "෴": 177, "෦": 178, "෧": 179, "෨": 180, "෩": 181, "෪": 182, "෫": 183, "෬": 184, "෭": 185, "෮": 186, "෯": 187, "ක්": 188, "කා": 189, "කි": 190, "කී": 191, "කු": 192, "කෙ": 193, "කො": 194, "කෝ": 195, "ග්": 196, "ගා": 197, "ගි": 198, "ගී": 199, "ගු": 200, "ගෙ": 201, "ගො": 202, "ගෝ": 203, "ත්": 204, "තා": 205, "ති": 206, "තී": 207, "තු": 208, "තෙ": 209, "තො": 210, "තෝ": 211, "න්": 212, "නා": 213, "නි": 214, "නී": 215, "නු": 216, "නෙ": 217, "නො": 218, "නෝ": 219, "බ්": 220, "බා": 221, "බි": 222, "බී": 223, "බු": 224, "බෙ": 225, "බො": 226, "බෝ": 227, "ම්": 228, "මා": 229, "මි": 230, "මී": 231, "මු": 232, "මෙ": 233, "මො": 234, "මෝ": 235, "ස්": 236, "සා": 237, "සි": 238, "සී": 239, "සු": 240, "සෙ": 241, "සො": 242, "සෝ": 243, "හ්": 244, "හා": 245, "හි": 246, "හී": 247, "හු": 248, "හෙ": 249, "හො": 250, "හෝ": 251, "ර්": 252, "රා": 253, "රි": 254, "රී": 255, "රු": 256, "රෙ": 257, "රො": 258, "රෝ": 259, "ල්": 260, "ලා": 261, "ලි": 262, "ලී": 263, "ලු": 264, "ලෙ": 265, "ලො": 266, "ලෝ": 267, "ය්": 268, "යා": 269, "යි": 270, "යී": 271, "යු": 272, "යෙ": 273, "යො": 274, "යෝ": 275, "ශ්": 276, "ශා": 277, "ශි": 278, "ශී": 279, "ශු": 280, "ශෙ": 281, "ශො": 282, "ශෝ": 283, "ව්": 284, "වා": 285, "වි": 286, "වී": 287, "වු": 288, "වෙ": 289, "වො": 290, "වෝ": 291, "ජ්": 292, "ජා": 293, "ජි": 294, "ජී": 295, "ජු": 296, "ජෙ": 297, "ජො": 298, "ජෝ": 299, "ට්": 300, "ටා": 301, "ටි": 302, "ටී": 303, "ටු": 304, "ටෙ": 305, "ටො": 306, "ටෝ": 307, "ඩ්": 308, "ඩා": 309, "ඩි": 310, "ඩී": 311, "ඩු": 312, "ඩෙ": 313, "ඩො": 314, "ඩෝ": 315, "ප්": 316, "පා": 317, "පි": 318, "පී": 319, "පු": 320, "පෙ": 321, "පො": 322, "පෝ": 323, "භ්": 324, "භා": 325, "භි": 326, "භී": 327, "භු": 328, "භෙ": 329, "භො": 330, "භෝ": 331, "ච්": 332, "චා": 333, "චි": 334, "චී": 335, "චු": 336, "චෙ": 337, "චො": 338, "චෝ": 339, "ද්": 340, "දා": 341, "දි": 342, "දී": 343, "දු": 344, "දෙ": 345, "දො": 346, "දෝ": 347, "ක්ෂ": 348, "ත්‍ර": 349, "න්ද": 350, "බ්ධ": 351, "ම්බ": 352, "ස්ථ": 353, "ද්ධ": 354, "න්ත": 355, "ප්ත": 356, "ල්බ": 357, "ජ්ජ": 358, "ණ්ඩ": 359, "ශ්‍ර": 360, "ක්ත": 361, "ග්න": 362, "ත්න": 363, "න්න": 364, "බ්බ": 365, "ම්ම": 366, "ර්න": 367, "ස්ස": 368, "හ්ම": 369, "ව්ව": 370, "ය්ය": 371, "ල්ල": 372, "ක්ක": 373, "ප්ප": 374, "ත්ත": 375, "ද්ද": 376, "ස්ක": 377, "ක්ල": 378, "ත්ල": 379, "ප්ල": 380, "බ්ර": 381, "ම්ර": 382, "ක්ග": 383, "ත්ග": 384, "ප්ග": 385, "බ්ග": 386, "ස්ග": 387, "ක්බ": 388, "ත්බ": 389, "ප්බ": 390, "ම්ප": 391, "ස්බ": 392, "එම": 393, "ඔහු": 394, "ඇය": 395, "මේ": 396, "එය": 397, "වන": 398, "කර": 399, "වේ": 400, "නම්": 401, "මත": 402, "බව": 403, "කළ": 404, "විය": 405, "ගියා": 406, "ආවා": 407, "කරනවා": 408, "කරන්න": 409, "යනවා": 410, "එනවා": 411, "වුණා": 412, "බැහැ": 413, "හැකි": 414, "වෙනවා": 415, "තිබෙනවා": 416, "හිටියා": 417, "රට": 418, "ලොව": 419, "මහ": 420, "ජන": 421, "සිය": 422, "කථා": 423, "ගීත": 424, "කලා": 425, "මන්ත්‍රී": 426, "ජනාධිපති": 427, "අගමැති": 428, "මන්ත්‍රණ": 429, "යුතු": 430, "ඉතා": 431, "විශේෂ": 432, "සහ": 433, "මුළු": 434, "පසු": 435, "පුරා": 436, "පමණ": 437, "සිට": 438, "සමග": 439, "තුළ": 440, "තම": 441, "අතර": 442, "සඳහා": 443, "එහි": 444, "මෙහි": 445, "වශයෙන්": 446, "නිසා": 447, "සෑම": 448, "ඉදිරි": 449, "ප්‍රධාන": 450, "ප්‍රති": 451, "විශාල": 452, "කුඩා": 453, "ප්‍රජා": 454, "නාගරික": 455, "ග්‍රාමීය": 456, "ජාතික": 457, "ජාත්‍යන්තර": 458, "සමාජ": 459, "ආර්ථික": 460, "දේශපාලන": 461, "සංස්කෘතික": 462, "ඓතිහාසික": 463, "පරිසර": 464, "සෞඛ්‍ය": 465, "අධ්‍යාපන": 466, "විද්‍යා": 467, "තාක්ෂණ": 468, "ගණිත": 469, "භාෂා": 470, "විශ්ව": 471, "වෙළඳ": 472, "කර්මාන්ත": 473, "සේවා": 474, "සංවර්ධන": 475, "ප්‍රතිපත්ති": 476, "යෝජනා": 477, "අවස්ථා": 478, "අනාගත": 479, "වර්තමාන": 480, "අතීත": 481, "සංගීත": 482, "නාට්‍ය": 483, "නැටුම්": 484, "චිත්‍ර": 485, "නිර්මාණ": 486, "සාහිත්‍ය": 487, "චරිත": 488, "පුස්තකාල": 489, "සම්මන්ත්‍රණ": 490, "ඉංග්‍රීසි": 491, "සිංහල": 492, "පර්යේෂණ": 493, "අධ්‍යයන": 494, "ක්ෂේත්‍ර": 495, "විශ්ලේෂණ": 496, "තක්සේරු": 497, "සාක්ෂි": 498, "උපකාර": 499, "සහයෝගය": 500, "ජයග්‍රහණ": 501, "අභියෝග": 502, "වාර්තා": 503, "තොරතුරු": 504, "තාක්ෂණය": 505, "පරිගණක": 506, "ජාලය": 507, "වෙබ්": 508, "මෘදුකාංග": 509, "පද්ධති": 510, "ක්‍රමය": 511, "ආකාරය": 512, "යෙදුම": 513, "සංකල්ප": 514, "අරමුණ": 515, "ඉලක්ක": 516, "ප්‍රතිඵල": 517, "ඵල": 518, "the": 519, "be": 520, "to": 521, "of": 522, "and": 523, "in": 524, "that": 525, "have": 526, "it": 527, "for": 528, "not": 529, "on": 530, "with": 531, "he": 532, "as": 533, "you": 534, "do": 535, "at": 536, "this": 537, "but": 538, "his": 539, "by": 540, "from": 541, "they": 542, "we": 543, "say": 544, "her": 545, "she": 546, "or": 547, "an": 548, "will": 549, "my": 550, "one": 551, "all": 552, "would": 553, "there": 554, "their": 555, "what": 556, "so": 557, "up": 558, "out": 559, "if": 560, "about": 561, "who": 562, "get": 563, "which": 564, "go": 565, "me": 566, "when": 567, "make": 568, "can": 569, "like": 570, "time": 571, "no": 572, "just": 573, "him": 574, "know": 575, "take": 576, "people": 577, "into": 578, "year": 579, "your": 580, "good": 581, "some": 582, "could": 583, "them": 584, "see": 585, "other": 586, "than": 587, "then": 588, "now": 589, "look": 590, "only": 591, "come": 592, "its": 593, "over": 594, "think": 595, "also": 596, "back": 597, "after": 598, "use": 599, "two": 600, "how": 601, "our": 602, "work": 603, "first": 604, "well": 605, "way": 606, "even": 607, "new": 608, "want": 609, "because": 610, "any": 611, "these": 612, "give": 613, "day": 614, "most": 615, "us": 616, "man": 617, "woman": 618, "child": 619, "world": 620, "life": 621, "hand": 622, "part": 623, "place": 624, "case": 625, "week": 626, "company": 627, "system": 628, "program": 629, "question": 630, "government": 631, "number": 632, "night": 633, "point": 634, "home": 635, "water": 636, "room": 637, "mother": 638, "area": 639, "money": 640, "story": 641, "fact": 642, "month": 643, "lot": 644, "right": 645, "study": 646, "book": 647, "eye": 648, "job": 649, "word": 650, "business": 651, "issue": 652, "side": 653, "kind": 654, "head": 655, "house": 656, "service": 657, "friend": 658, "father": 659, "power": 660, "hour": 661, "game": 662, "line": 663, "end": 664, "member": 665, "law": 666, "car": 667, "city": 668, "community": 669, "name": 670, "president": 671, "team": 672, "minute": 673, "idea": 674, "body": 675, "information": 676, "river": 677, "land": 678, "building": 679, "action": 680, "full": 681, "class": 682, "mark": 683, "level": 684, "door": 685, "health": 686, "person": 687, "art": 688, "war": 689, "history": 690, "party": 691, "result": 692, "change": 693, "morning": 694, "reason": 695, "research": 696, "girl": 697, "guy": 698, "moment": 699, "air": 700, "teacher": 701, "force": 702, "education": 703, "state": 704, "country": 705, "problem": 706, "group": 707, "school": 708, "student": 709, "family": 710, "children": 711, "run": 712, "walk": 713, "stop": 714, "speak": 715, "read": 716, "allow": 717, "spend": 718, "grow": 719, "open": 720, "win": 721, "offer": 722, "remember": 723, "love": 724, "consider": 725, "appear": 726, "buy": 727, "wait": 728, "serve": 729, "send": 730, "expect": 731, "build": 732, "stay": 733, "fall": 734, "cut": 735, "reach": 736, "kill": 737, "remain": 738, "suggest": 739, "raise": 740, "pass": 741, "sell": 742, "require": 743, "report": 744, "decide": 745, "pull": 746, "develop": 747, "eat": 748, "produce": 749, "carry": 750, "talk": 751, "turn": 752, "start": 753, "show": 754, "hear": 755, "play": 756, "move": 757, "live": 758, "bring": 759, "happen": 760, "write": 761, "sit": 762, "stand": 763, "lose": 764, "pay": 765, "meet": 766, "set": 767, "learn": 768, "lead": 769, "understand": 770, "watch": 771, "create": 772, "leave": 773, "put": 774, "mean": 775, "keep": 776, "let": 777, "begin": 778, "seem": 779, "help": 780, "tell": 781, "feel": 782, "try": 783, "ask": 784, "need": 785, "become": 786, "long": 787, "high": 788, "old": 789, "different": 790, "small": 791, "large": 792, "next": 793, "young": 794, "important": 795, "few": 796, "public": 797, "bad": 798, "same": 799, "able": 800, "great": 801, "little": 802, "big": 803, "real": 804, "best": 805, "better": 806, "sure": 807, "free": 808, "strong": 809, "true": 810, "whole": 811, "white": 812, "black": 813, "red": 814, "blue": 815, "green": 816, "dark": 817, "hard": 818, "soft": 819, "hot": 820, "cold": 821, "fast": 822, "slow": 823, "clean": 824, "safe": 825, "quiet": 826, "deep": 827, "wide": 828, "flat": 829, "round": 830, "thick": 831, "thin": 832, "light": 833, "heavy": 834, "dry": 835, "wet": 836, "empty": 837, "close": 838, "simple": 839, "difficult": 840, "possible": 841, "necessary": 842, "very": 843, "often": 844, "never": 845, "always": 846, "sometimes": 847, "here": 848, "still": 849, "already": 850, "together": 851, "quickly": 852, "slowly": 853, "recently": 854, "finally": 855, "suddenly": 856, "almost": 857, "enough": 858, "really": 859, "quite": 860, "rather": 861, "too": 862, "perhaps": 863, "certainly": 864, "probably": 865, "actually": 866, "especially": 867, "generally": 868, "immediately": 869, "simply": 870, "directly": 871, "closely": 872, "seriously": 873, "currently": 874, "between": 875, "through": 876, "before": 877, "during": 878, "while": 879, "without": 880, "within": 881, "along": 882, "toward": 883, "since": 884, "until": 885, "against": 886, "among": 887, "across": 888, "under": 889, "around": 890, "upon": 891, "above": 892, "below": 893, "beyond": 894, "behind": 895, "beside": 896, "besides": 897, "beneath": 898, "despite": 899, "except": 900, "although": 901, "though": 902, "whether": 903, "whereas": 904, "whereby": 905, "second": 906, "third": 907, "fourth": 908, "fifth": 909, "hundred": 910, "thousand": 911, "million": 912, "billion": 913, "today": 914, "tomorrow": 915, "yesterday": 916, "afternoon": 917, "evening": 918, "season": 919, "spring": 920, "summer": 921, "autumn": 922, "winter": 923, "daily": 924, "weekly": 925, "monthly": 926, "yearly": 927, "ing": 928, "tion": 929, "sion": 930, "ness": 931, "ment": 932, "ible": 933, "ful": 934, "less": 935, "ous": 936, "ive": 937, "ally": 938, "ence": 939, "ance": 940, "ity": 941, "ent": 942, "ant": 943, "ical": 944, "ure": 945, "dom": 946, "ship": 947, "ward": 948, "wise": 949, "ling": 950, "ette": 951, "hood": 952, "ery": 953, "ary": 954, "ory": 955, "fy": 956, "ize": 957, "ise": 958, "ify": 959, "ial": 960, "ual": 961, "ers": 962, "est": 963, "ors": 964, "ist": 965, "ism": 966, "ian": 967, "ese": 968, "ish": 969, "un": 970, "re": 971, "pre": 972, "dis": 973, "mis": 974, "inter": 975, "trans": 976, "sub": 977, "super": 978, "anti": 979, "de": 980, "im": 981, "non": 982, "pro": 983, "multi": 984, "semi": 985, "auto": 986, "co": 987, "bi": 988, "tri": 989, "poly": 990, "mono": 991, "post": 992, "mid": 993, "fore": 994, "self": 995, "mal": 996, "bene": 997, "circum": 998, "counter": 999, "ex": 1000, "extra": 1001, "hyper": 1002, "intra": 1003, "macro": 1004, "micro": 1005, "neo": 1006, "omni": 1007, "para": 1008, "peri": 1009, "proto": 1010, "pseudo": 1011, "retro": 1012, "th": 1013, "er": 1014, "en": 1015, "nd": 1016, "ti": 1017, "es": 1018, "te": 1019, "ed": 1020, "is": 1021, "al": 1022, "ar": 1023, "st": 1024, "nt": 1025, "ng": 1026, "se": 1027, "ha": 1028, "ou": 1029, "io": 1030, "le": 1031, "ve": 1032, "hi": 1033, "ri": 1034, "ro": 1035, "ic": 1036, "ne": 1037, "ea": 1038, "wh": 1039, "pr": 1040, "sh": 1041, "tr": 1042, "ch": 1043, "ph": 1044, "gr": 1045, "sp": 1046, "cl": 1047, "tha": 1048, "hat": 1049, "wit": 1050, "thi": 1051, "ion": 1052, "ati": 1053, "ter": 1054, "ted": 1055, "ith": 1056, "oth": 1057, "ght": 1058, "ich": 1059, "ble": 1060, "con": 1061, "data": 1062, "model": 1063, "train": 1064, "test": 1065, "loss": 1066, "cost": 1067, "task": 1068, "code": 1069, "file": 1070, "type": 1071, "func": 1072, "void": 1073, "false": 1074, "null": 1075, "none": 1076, "init": 1077, "main": 1078, "base": 1079, "tail": 1080, "root": 1081, "leaf": 1082, "node": 1083, "edge": 1084, "path": 1085, "loop": 1086, "list": 1087, "dict": 1088, "map": 1089, "key": 1090, "val": 1091, "pop": 1092, "push": 1093, "size": 1094, "len": 1095, "min": 1096, "max": 1097, "sum": 1098, "avg": 1099, "count": 1100, "range": 1101, "step": 1102, "each": 1103, "item": 1104, "elem": 1105, "idx": 1106, "index": 1107, "value": 1108, "text": 1109, "sent": 1110, "char": 1111, "byte": 1112, "flag": 1113, "mode": 1114, "sort": 1115, "≠": 1116, "≈": 1117, "≡": 1118, "≤": 1119, "≥": 1120, "±": 1121, "∓": 1122, "×": 1123, "÷": 1124, "∛": 1125, "∜": 1126, "≶": 1127, "≷": 1128, "≺": 1129, "≻": 1130, "≼": 1131, "≽": 1132, "≪": 1133, "≫": 1134, "∈": 1135, "∉": 1136, "⊂": 1137, "⊃": 1138, "⊆": 1139, "⊇": 1140, "∪": 1141, "∩": 1142, "∅": 1143, "∖": 1144, "∀": 1145, "∃": 1146, "¬": 1147, "∧": 1148, "∨": 1149, "⊕": 1150, "⊗": 1151, "⊙": 1152, "⊢": 1153, "⊣": 1154, "⊨": 1155, "∂": 1156, "∇": 1157, "∫": 1158, "∬": 1159, "∭": 1160, "∮": 1161, "∯": 1162, "∰": 1163, "∑": 1164, "∏": 1165, "lim": 1166, "α": 1167, "β": 1168, "γ": 1169, "δ": 1170, "ε": 1171, "ζ": 1172, "η": 1173, "θ": 1174, "ι": 1175, "κ": 1176, "λ": 1177, "μ": 1178, "ν": 1179, "ξ": 1180, "π": 1181, "ρ": 1182, "σ": 1183, "τ": 1184, "υ": 1185, "φ": 1186, "χ": 1187, "ψ": 1188, "ω": 1189, "ϵ": 1190, "ϑ": 1191, "ϰ": 1192, "ϱ": 1193, "ϖ": 1194, "ς": 1195, "Γ": 1196, "Δ": 1197, "Θ": 1198, "Λ": 1199, "Ξ": 1200, "Π": 1201, "Σ": 1202, "Υ": 1203, "Φ": 1204, "Ψ": 1205, "Ω": 1206, "→": 1207, "←": 1208, "↔": 1209, "⇒": 1210, "⇐": 1211, "⇔": 1212, "↦": 1213, "⟼": 1214, "↑": 1215, "↓": 1216, "↗": 1217, "↘": 1218, "↖": 1219, "↙": 1220, "⟂": 1221, "∥": 1222, "sin": 1223, "cos": 1224, "tan": 1225, "cot": 1226, "sec": 1227, "csc": 1228, "sinh": 1229, "cosh": 1230, "tanh": 1231, "arcsin": 1232, "arccos": 1233, "arctan": 1234, "log": 1235, "ln": 1236, "exp": 1237, "sup": 1238, "inf": 1239, "gcd": 1240, "lcm": 1241, "mod": 1242, "div": 1243, "ℝ": 1244, "ℂ": 1245, "ℤ": 1246, "ℕ": 1247, "ℚ": 1248, "ℙ": 1249, "x²": 1250, "x³": 1251, "xⁿ": 1252, "xᵢ": 1253, "xⱼ": 1254, "a²": 1255, "b²": 1256, "c²": 1257, "n²": 1258, "n³": 1259, "R²": 1260, "R³": 1261, "Rⁿ": 1262, "C²": 1263, "dx": 1264, "dy": 1265, "dz": 1266, "dt": 1267, "df": 1268, "dg": 1269, "dh": 1270, "∂x": 1271, "∂y": 1272, "∂z": 1273, "∂t": 1274, "λ₁": 1275, "λ₂": 1276, "λ₃": 1277, "λₙ": 1278, "α₁": 1279, "α₂": 1280, "α₃": 1281, "β₁": 1282, "β₂": 1283, "β₃": 1284, "σ²": 1285, "σ₁": 1286, "σ₂": 1287, "σₙ": 1288, "μ₁": 1289, "μ₂": 1290, "μ₃": 1291, "μₙ": 1292, "θ₁": 1293, "θ₂": 1294, "θ₃": 1295, "θₙ": 1296, "ω₁": 1297, "ω₂": 1298, "ω₃": 1299, "w₁": 1300, "w₂": 1301, "w₃": 1302, "wᵢ": 1303, "wⱼ": 1304, "b₁": 1305, "b₂": 1306, "b₃": 1307, "bᵢ": 1308, "i²": 1309, "j²": 1310, "k²": 1311, "‖x‖": 1312, "|x|": 1313, "‖A‖": 1314, "Aᵀ": 1315, "A⁻¹": 1316, "A*": 1317, "A^T": 1318, "A^H": 1319, "⟨x,y⟩": 1320, "⟨x⟩": 1321, "‖·‖": 1322, "O(n)": 1323, "O(n²)": 1324, "O(log n)": 1325, "O(1)": 1326, "O(n log n)": 1327, "e^x": 1328, "e^i": 1329, "π²": 1330, "\\frac": 1331, "\\dfrac": 1332, "\\tfrac": 1333, "\\cfrac": 1334, "\\sqrt": 1335, "\\sqrt[n]": 1336, "\\sum": 1337, "\\prod": 1338, "\\int": 1339, "\\iint": 1340, "\\iiint": 1341, "\\oint": 1342, "\\limits": 1343, "\\nolimits": 1344, "\\lim": 1345, "\\limsup": 1346, "\\liminf": 1347, "\\sup": 1348, "\\inf": 1349, "\\max": 1350, "\\min": 1351, "\\log": 1352, "\\ln": 1353, "\\exp": 1354, "\\sin": 1355, "\\cos": 1356, "\\tan": 1357, "\\cot": 1358, "\\sec": 1359, "\\csc": 1360, "\\sinh": 1361, "\\cosh": 1362, "\\tanh": 1363, "\\arcsin": 1364, "\\arccos": 1365, "\\arctan": 1366, "\\floor": 1367, "\\ceil": 1368, "\\abs": 1369, "\\norm": 1370, "\\det": 1371, "\\alpha": 1372, "\\beta": 1373, "\\gamma": 1374, "\\delta": 1375, "\\epsilon": 1376, "\\varepsilon": 1377, "\\zeta": 1378, "\\eta": 1379, "\\theta": 1380, "\\vartheta": 1381, "\\iota": 1382, "\\kappa": 1383, "\\lambda": 1384, "\\mu": 1385, "\\nu": 1386, "\\xi": 1387, "\\pi": 1388, "\\varpi": 1389, "\\rho": 1390, "\\varrho": 1391, "\\sigma": 1392, "\\varsigma": 1393, "\\tau": 1394, "\\upsilon": 1395, "\\phi": 1396, "\\varphi": 1397, "\\chi": 1398, "\\psi": 1399, "\\omega": 1400, "\\Gamma": 1401, "\\Delta": 1402, "\\Theta": 1403, "\\Lambda": 1404, "\\Xi": 1405, "\\Pi": 1406, "\\Sigma": 1407, "\\Upsilon": 1408, "\\Phi": 1409, "\\Psi": 1410, "\\Omega": 1411, "\\rightarrow": 1412, "\\leftarrow": 1413, "\\leftrightarrow": 1414, "\\Rightarrow": 1415, "\\Leftarrow": 1416, "\\Leftrightarrow": 1417, "\\mapsto": 1418, "\\longmapsto": 1419, "\\uparrow": 1420, "\\downarrow": 1421, "\\updownarrow": 1422, "\\leq": 1423, "\\geq": 1424, "\\neq": 1425, "\\approx": 1426, "\\equiv": 1427, "\\sim": 1428, "\\simeq": 1429, "\\cong": 1430, "\\propto": 1431, "\\ll": 1432, "\\gg": 1433, "\\lesssim": 1434, "\\gtrsim": 1435, "\\lessgtr": 1436, "\\preceq": 1437, "\\succeq": 1438, "\\subset": 1439, "\\supset": 1440, "\\subseteq": 1441, "\\supseteq": 1442, "\\in": 1443, "\\notin": 1444, "\\ni": 1445, "\\sqsubset": 1446, "\\sqsupset": 1447, "\\sqsubseteq": 1448, "\\sqsupseteq": 1449, "\\cup": 1450, "\\cap": 1451, "\\setminus": 1452, "\\emptyset": 1453, "\\varnothing": 1454, "\\cdot": 1455, "\\times": 1456, "\\div": 1457, "\\pm": 1458, "\\mp": 1459, "\\circ": 1460, "\\bullet": 1461, "\\star": 1462, "\\ast": 1463, "\\dagger": 1464, "\\hat": 1465, "\\widehat": 1466, "\\bar": 1467, "\\overline": 1468, "\\tilde": 1469, "\\widetilde": 1470, "\\vec": 1471, "\\overrightarrow": 1472, "\\dot": 1473, "\\ddot": 1474, "\\ddddot": 1475, "\\check": 1476, "\\breve": 1477, "\\acute": 1478, "\\grave": 1479, "\\overbrace": 1480, "\\underbrace": 1481, "\\text": 1482, "\\textrm": 1483, "\\textbf": 1484, "\\textit": 1485, "\\texttt": 1486, "\\textsf": 1487, "\\textsc": 1488, "\\emph": 1489, "\\mathrm": 1490, "\\mathbf": 1491, "\\mathit": 1492, "\\mathsf": 1493, "\\mathtt": 1494, "\\mathcal": 1495, "\\mathbb": 1496, "\\mathfrak": 1497, "\\mathscr": 1498, "\\begin": 1499, "\\end": 1500, "equation": 1501, "equation*": 1502, "align": 1503, "align*": 1504, "gather": 1505, "gather*": 1506, "multline": 1507, "multline*": 1508, "matrix": 1509, "pmatrix": 1510, "bmatrix": 1511, "vmatrix": 1512, "Vmatrix": 1513, "cases": 1514, "array": 1515, "aligned": 1516, "gathered": 1517, "split": 1518, "eqnarray": 1519, "flalign": 1520, "flalign*": 1521, "\\quad": 1522, "\\qquad": 1523, "\\,": 1524, "\\;": 1525, "\\:": 1526, "\\!": 1527, "\\enspace": 1528, "\\left": 1529, "\\right": 1530, "\\middle": 1531, "\\Big": 1532, "\\big": 1533, "\\overset": 1534, "\\underset": 1535, "\\substack": 1536, "\\item": 1537, "\\enumerate": 1538, "\\itemize": 1539, "\\description": 1540, "\\section": 1541, "\\section*": 1542, "\\subsection": 1543, "\\subsection*": 1544, "\\subsubsection": 1545, "\\chapter": 1546, "\\paragraph": 1547, "\\subparagraph": 1548, "\\documentclass": 1549, "\\usepackage": 1550, "\\title": 1551, "\\author": 1552, "\\date": 1553, "\\maketitle": 1554, "\\tableofcontents": 1555, "\\listoffigures": 1556, "\\listoftables": 1557, "\\newpage": 1558, "\\clearpage": 1559, "\\pagebreak": 1560, "\\linebreak": 1561, "\\includegraphics": 1562, "\\resizebox": 1563, "\\scalebox": 1564, "\\caption": 1565, "\\label": 1566, "\\ref": 1567, "\\eqref": 1568, "\\autoref": 1569, "\\cite": 1570, "\\citep": 1571, "\\citet": 1572, "\\citeauthor": 1573, "\\bibliography": 1574, "\\bibliographystyle": 1575, "\\hline": 1576, "\\cline": 1577, "\\multicolumn": 1578, "\\multirow": 1579, "\\toprule": 1580, "\\midrule": 1581, "\\bottomrule": 1582, "\\fbox": 1583, "\\mbox": 1584, "\\hbox": 1585, "\\vbox": 1586, "\\to": 1587, "\\gets": 1588, "\\therefore": 1589, "\\because": 1590, "\\ldots": 1591, "\\cdots": 1592, "\\vdots": 1593, "\\ddots": 1594, "\\hdots": 1595, "\\langle": 1596, "\\rangle": 1597, "\\lfloor": 1598, "\\rfloor": 1599, "\\lceil": 1600, "\\rceil": 1601, "\\lvert": 1602, "\\rvert": 1603, "\\lVert": 1604, "\\rVert": 1605, "p{": 1606, "m{": 1607, "b{": 1608, "\\frac{d}{dx}": 1609, "\\frac{\\partial}{\\partial x}": 1610, "\\frac{1}{n}": 1611, "\\frac{1}{2}": 1612, "\\sum_{i=0}^{n}": 1613, "\\prod_{i=1}^{n}": 1614, "\\int_{a}^{b}": 1615, "\\lim_{x \\to \\infty}": 1616, "\\mathbb{R}": 1617, "\\mathbb{C}": 1618, "\\mathbb{Z}": 1619, "\\mathbb{N}": 1620, "\\mathcal{L}": 1621, "\\mathcal{F}": 1622, "\\mathcal{N}": 1623, "\\left(": 1624, "\\right)": 1625, "\\left[": 1626, "\\right]": 1627, "\\left\\{": 1628, "\\right\\}": 1629, "\\left|": 1630, "\\right|": 1631, "langchain": 1632, "LangChain": 1633, "langchain_core": 1634, "langchain_community": 1635, "LLMChain": 1636, "PromptTemplate": 1637, "ChatOpenAI": 1638, "OpenAI": 1639, "ConversationChain": 1640, "ChatPromptTemplate": 1641, "FewShotPromptTemplate": 1642, "PipelinePromptTemplate": 1643, "SystemMessagePromptTemplate": 1644, "HumanMessagePromptTemplate": 1645, "AIMessagePromptTemplate": 1646, "MessagePlaceholder": 1647, "BaseMessage": 1648, "HumanMessage": 1649, "AIMessage": 1650, "SystemMessage": 1651, "FunctionMessage": 1652, "ChatMessage": 1653, "memory": 1654, "ConversationBufferMemory": 1655, "ConversationSummaryMemory": 1656, "ConversationBufferWindowMemory": 1657, "ConversationEntityMemory": 1658, "ConversationTokenBufferMemory": 1659, "Memory": 1660, "BaseMemory": 1661, "document_loaders": 1662, "WebBaseLoader": 1663, "CSVLoader": 1664, "PyPDFLoader": 1665, "TextLoader": 1666, "DirectoryLoader": 1667, "JSONLoader": 1668, "UnstructuredMarkdownLoader": 1669, "NotionDirectoryLoader": 1670, "S3DirectoryLoader": 1671, "GitbookLoader": 1672, "AirbyteJSONLoader": 1673, "text_splitter": 1674, "RecursiveCharacterTextSplitter": 1675, "CharacterTextSplitter": 1676, "HTMLHeaderTextSplitter": 1677, "MarkdownHeaderTextSplitter": 1678, "TokenTextSplitter": 1679, "Language": 1680, "RecursiveUrlLoader": 1681, "embeddings": 1682, "Embeddings": 1683, "HuggingFaceEmbeddings": 1684, "OpenAIEmbeddings": 1685, "CohereEmbeddings": 1686, "SentenceTransformerEmbeddings": 1687, "FakeEmbeddings": 1688, "vectorstore": 1689, "VectorStore": 1690, "Chroma": 1691, "FAISS": 1692, "Pinecone": 1693, "Weaviate": 1694, "Qdrant": 1695, "Milvus": 1696, "ChromaVectorStore": 1697, "FAISSVectorStore": 1698, "VectorStoreRetriever": 1699, "retriever": 1700, "Retriever": 1701, "SelfQueryRetriever": 1702, "MultiQueryRetriever": 1703, "ContextualCompressionRetriever": 1704, "RetrievalQA": 1705, "chain": 1706, "Chain": 1707, "SequentialChain": 1708, "SimpleSequentialChain": 1709, "TransformChain": 1710, "RouterChain": 1711, "create_retrieval_chain": 1712, "create_stuff_documents_chain": 1713, "create_history_aware_retriever": 1714, "create_citation_fuzzy_link": 1715, "agent": 1716, "Agent": 1717, "AgentExecutor": 1718, "create_react_agent": 1719, "create_openai_functions_agent": 1720, "create_openai_tools_agent": 1721, "ZeroShotAgent": 1722, "StructuredInputAgent": 1723, "OpenAIAgent": 1724, "ToolCallingAgent": 1725, "tool": 1726, "Tool": 1727, "BaseTool": 1728, "StructuredTool": 1729, "DuckDuckGoSearchRun": 1730, "WikipediaQueryRun": 1731, "GoogleSearchAPIWrapper": 1732, "SerpAPIWrapper": 1733, "RunnableSequence": 1734, "RunnablePassthrough": 1735, "RunnableLambda": 1736, "RunnableParallel": 1737, "RunnableConfig": 1738, "RunnableWithMessageHistory": 1739, "RunnableBranch": 1740, "RunnableRetry": 1741, "StrOutputParser": 1742, "JsonOutputParser": 1743, "PydanticOutputParser": 1744, "BytesOutputParser": 1745, "CommaSeparatedListOutputParser": 1746, "SimpleJsonOutputParser": 1747, "StructuredOutputParser": 1748, "RetryOutputParser": 1749, "callbacks": 1750, "CallbackManager": 1751, "CallbackHandler": 1752, "StreamingStdOutCallbackHandler": 1753, "StdOutCallbackHandler": 1754, "WandbCallbackHandler": 1755, "AsyncCallbackHandler": 1756, "StateGraph": 1757, "MessageGraph": 1758, "END": 1759, "START": 1760, "add_node": 1761, "add_edge": 1762, "add_conditional_edges": 1763, "invoke": 1764, "ainvoke": 1765, "stream": 1766, "astream": 1767, "batch": 1768, "abatch": 1769, "pipe": 1770, "Document": 1771, "page_content": 1772, "metadata": 1773, "evaluation": 1774, "QAEvalChain": 1775, "LangChainStringEvaluator": 1776, "document_transformers": 1777, "EmbeddingsRedundantFilter": 1778, "EmbeddingsFilter": 1779, "DocumentCompressorPipeline": 1780, "LLMChainExtractor": 1781, "get_openai_callback": 1782, "get_num_tokens_from_text": 1783, "encode": 1784, "decode": 1785, "tokenize": 1786, "format_to_openai_function": 1787, "format_to_openai_tool": 1788, "neural": 1789, "network": 1790, "layer": 1791, "neuron": 1792, "weight": 1793, "bias": 1794, "activation": 1795, "activation_function": 1796, "relu": 1797, "sigmoid": 1798, "softmax": 1799, "gelu": 1800, "swish": 1801, "silu": 1802, "leaky_relu": 1803, "elu": 1804, "selu": 1805, "prelu": 1806, "mish": 1807, "retention": 1808, "retention_network": 1809, "retention_score": 1810, "retention_heads": 1811, "retention_dim": 1812, "retention_layers": 1813, "multi_scale": 1814, "decay": 1815, "exponential_decay": 1816, "chunk": 1817, "chunkwise": 1818, "recurrent": 1819, "parallel": 1820, "gamma": 1821, "retention_matrix": 1822, "retention_Q": 1823, "retention_K": 1824, "retention_V": 1825, "transformer": 1826, "attention": 1827, "self_attention": 1828, "cross_attention": 1829, "multi_head": 1830, "head_dim": 1831, "num_heads": 1832, "num_layers": 1833, "hidden_dim": 1834, "ffn_dim": 1835, "context_length": 1836, "positional_encoding": 1837, "positional_embedding": 1838, "rotary": 1839, "rope": 1840, "alibi": 1841, "query": 1842, "qkv": 1843, "attention_mask": 1844, "causal_mask": 1845, "padding_mask": 1846, "linear_attention": 1847, "state_space": 1848, "ssm": 1849, "mamba": 1850, "rwkv": 1851, "s4": 1852, "h3": 1853, "gated_linear": 1854, "training": 1855, "training_loss": 1856, "validation_loss": 1857, "test_loss": 1858, "epoch": 1859, "batch_size": 1860, "learning_rate": 1861, "lr": 1862, "optimizer": 1863, "adam": 1864, "adamw": 1865, "sgd": 1866, "rmsprop": 1867, "scheduler": 1868, "warmup": 1869, "cosine_schedule": 1870, "gradient": 1871, "backpropagation": 1872, "backward": 1873, "forward": 1874, "cross_entropy": 1875, "mse": 1876, "mae": 1877, "nll_loss": 1878, "dropout": 1879, "regularization": 1880, "weight_decay": 1881, "gradient_clipping": 1882, "gradient_accumulation": 1883, "mixed_precision": 1884, "fp16": 1885, "bf16": 1886, "fp32": 1887, "encoder": 1888, "decoder": 1889, "embedding": 1890, "token_embedding": 1891, "position_embedding": 1892, "segment_embedding": 1893, "layernorm": 1894, "layer_norm": 1895, "rmsnorm": 1896, "group_norm": 1897, "batch_norm": 1898, "instance_norm": 1899, "pre_norm": 1900, "post_norm": 1901, "residual": 1902, "skip_connection": 1903, "dataset": 1904, "dataloader": 1905, "tokenizer": 1906, "vocabulary": 1907, "sequence": 1908, "token": 1909, "tokens": 1910, "detokenize": 1911, "padding": 1912, "truncation": 1913, "max_length": 1914, "input_ids": 1915, "labels": 1916, "pretraining": 1917, "finetuning": 1918, "fine_tuning": 1919, "transfer_learning": 1920, "few_shot": 1921, "zero_shot": 1922, "in_context": 1923, "instruction_tuning": 1924, "accuracy": 1925, "precision": 1926, "recall": 1927, "f1_score": 1928, "perplexity": 1929, "bleu": 1930, "rouge": 1931, "meteor": 1932, "pytorch": 1933, "torch": 1934, "tensorflow": 1935, "keras": 1936, "jax": 1937, "flax": 1938, "huggingface": 1939, "transformers": 1940, "datasets": 1941, "generate": 1942, "generation": 1943, "beam_search": 1944, "greedy": 1945, "top_k": 1946, "top_p": 1947, "temperature": 1948, "sampling": 1949, "autoregressive": 1950, "seq2seq": 1951, "denoising": 1952, "bert": 1953, "gpt": 1954, "llama": 1955, "mistral": 1956, "albert": 1957, "roberta": 1958, "deberta": 1959, "electra": 1960, "t5": 1961, "bart": 1962, "pegasus": 1963, "longformer": 1964, "convex": 1965, "convergence": 1966, "optimization": 1967, "hyperparameter": 1968, "grid_search": 1969, "bayesian_optimization": 1970, "distributed": 1971, "data_parallel": 1972, "model_parallel": 1973, "pipeline_parallel": 1974, "fsdp": 1975, "deepspeed": 1976, "zero": 1977, "flash_attention": 1978, "flash_attn": 1979, "memory_efficient": 1980, "bce_loss": 1981, "focal_loss": 1982, "contrastive_loss": 1983, "triplet_loss": 1984, "kl_divergence": 1985, "js_divergence": 1986, "wasserstein": 1987, "earth_mover": 1988, "group_query": 1989, "gqa": 1990, "mqa": 1991, "mha": 1992, "sparse_attention": 1993, "scaling_law": 1994, "scaling": 1995, "chinchilla": 1996, "compute_optimal": 1997, "inference_optimal": 1998, "def": 1999, "return": 2000, "import": 2001, "elif": 2002, "else": 2003, "yield": 2004, "lambda": 2005, "break": 2006, "continue": 2007, "assert": 2008, "del": 2009, "global": 2010, "nonlocal": 2011, "async": 2012, "await": 2013, "print": 2014, "enumerate": 2015, "zip": 2016, "filter": 2017, "sorted": 2018, "reversed": 2019, "tuple": 2020, "int": 2021, "float": 2022, "str": 2023, "bool": 2024, "None": 2025, "True": 2026, "False": 2027, "isinstance": 2028, "hasattr": 2029, "getattr": 2030, "setattr": 2031, "object": 2032, "property": 2033, "List": 2034, "Dict": 2035, "Set": 2036, "Tuple": 2037, "Optional": 2038, "Union": 2039, "Any": 2040, "Callable": 2041, "Iterator": 2042, "Generator": 2043, "Class": 2044, "Type": 2045, "Sequence": 2046, "Mapping": 2047, "Literal": 2048, "Annotated": 2049, "Protocol": 2050, "TypeVar": 2051, "__init__": 2052, "__str__": 2053, "__repr__": 2054, "__len__": 2055, "__getitem__": 2056, "__setitem__": 2057, "__call__": 2058, "__enter__": 2059, "__exit__": 2060, "__iter__": 2061, "__eq__": 2062, "__lt__": 2063, "__gt__": 2064, "__hash__": 2065, "append": 2066, "extend": 2067, "insert": 2068, "remove": 2069, "clear": 2070, "keys": 2071, "values": 2072, "items": 2073, "update": 2074, "merge": 2075, "add": 2076, "discard": 2077, "union": 2078, "intersection": 2079, "difference": 2080, "flush": 2081, "seek": 2082, "readline": 2083, "readlines": 2084, "writelines": 2085, "join": 2086, "strip": 2087, "replace": 2088, "find": 2089, "upper": 2090, "lower": 2091, "title": 2092, "capitalize": 2093, "format": 2094, "startswith": 2095, "endswith": 2096, "isdigit": 2097, "isalpha": 2098, "os": 2099, "sys": 2100, "json": 2101, "math": 2102, "random": 2103, "datetime": 2104, "collections": 2105, "functools": 2106, "itertools": 2107, "pathlib": 2108, "commit": 2109, "branch": 2110, "clone": 2111, "status": 2112, "diff": 2113, "stash": 2114, "typing": 2115, "dataclasses": 2116, "enum": 2117, "logging": 2118, "unittest": 2119, "pytest": 2120, "copy": 2121, "__name__": 2122, "__main__": 2123, "__file__": 2124, "__all__": 2125, "argparse": 2126, "click": 2127, "typer": 2128, "subprocess": 2129, "request": 2130, "response": 2131, "server": 2132, "client": 2133, "endpoint": 2134, "route": 2135, "handler": 2136, "middleware": 2137, "thread": 2138, "process": 2139, "lock": 2140, "semaphore": 2141, "queue": 2142, "asyncio": 2143, "aiohttp": 2144, "httpx": 2145, "mock": 2146, "patch": 2147, "fixture": 2148, "assertEqual": 2149, "assertRaises": 2150, "setUp": 2151, "tearDown": 2152, "tokenization": 2153, "subword": 2154, "wordpiece": 2155, "bpe": 2156, "sentencepiece": 2157, "unigram": 2158, "vocab": 2159, "corpus": 2160, "corpora": 2161, "stemming": 2162, "lemmatization": 2163, "pos_tag": 2164, "ner": 2165, "named_entity": 2166, "dependency_parse": 2167, "constituency_parse": 2168, "sentiment": 2169, "sentiment_analysis": 2170, "text_classification": 2171, "text_generation": 2172, "text_summarization": 2173, "text_completion": 2174, "question_answering": 2175, "dialogue": 2176, "dialogue_system": 2177, "machine_translation": 2178, "named_entity_recognition": 2179, "relation_extraction": 2180, "information_extraction": 2181, "information_retrieval": 2182, "text_mining": 2183, "language_model": 2184, "lm": 2185, "encoder_decoder": 2186, "word_embedding": 2187, "contextual_embedding": 2188, "pretrained": 2189, "pre_trained": 2190, "fine_tune": 2191, "finetune": 2192, "inference": 2193, "validation": 2194, "testing": 2195, "prompt": 2196, "prompting": 2197, "in_context_learning": 2198, "chain_of_thought": 2199, "instruction": 2200, "instruction_following": 2201, "retrieval_augmented": 2202, "rag": 2203, "chunking": 2204, "chunk_size": 2205, "overlap": 2206, "context_window": 2207, "embedding_model": 2208, "vector_database": 2209, "vector_db": 2210, "semantic_search": 2211, "keyword_search": 2212, "hybrid_search": 2213, "document": 2214, "passage": 2215, "paragraph": 2216, "sentence": 2217, "character": 2218, "bleu_score": 2219, "rouge_score": 2220, "nucleus": 2221, "greedy_search": 2222, "stop_token": 2223, "end_token": 2224, "start_token": 2225, "pad_token": 2226, "unk_token": 2227, "mask_token": 2228, "cls_token": 2229, "sep_token": 2230, "hallucination": 2231, "grounding": 2232, "rlhf": 2233, "dpo": 2234, "ppo": 2235, "reward_model": 2236, "alignment": 2237, "safety": 2238, "guardrails": 2239, "multilingual": 2240, "cross_lingual": 2241, "code_switching": 2242, "abstractive": 2243, "extractive": 2244, "multi_document": 2245, "dense_retrieval": 2246, "sparse_retrieval": 2247, "colbert": 2248, "dpr": 2249, "sentence_embedding": 2250, "abstract": 2251, "introduction": 2252, "methodology": 2253, "method": 2254, "experiment": 2255, "experiments": 2256, "results": 2257, "discussion": 2258, "conclusion": 2259, "related_work": 2260, "appendix": 2261, "references": 2262, "figure": 2263, "table": 2264, "caption": 2265, "footnote": 2266, "notation": 2267, "hypothesis": 2268, "theorem": 2269, "lemma": 2270, "corollary": 2271, "proposition": 2272, "definition": 2273, "axiom": 2274, "proof": 2275, "conjecture": 2276, "assumption": 2277, "draft": 2278, "revision": 2279, "review": 2280, "submission": 2281, "journal": 2282, "conference": 2283, "workshop": 2284, "symposium": 2285, "proceedings": 2286, "volume": 2287, "doi": 2288, "citation": 2289, "bibliography": 2290, "acknowledgment": 2291, "machine_learning": 2292, "deep_learning": 2293, "natural_language": 2294, "artificial_intelligence": 2295, "data_science": 2296, "reinforcement_learning": 2297, "supervised_learning": 2298, "unsupervised_learning": 2299, "federated_learning": 2300, "multi_modal": 2301, "cross_modal": 2302, "knowledge_graph": 2303, "knowledge_base": 2304, "speech_recognition": 2305, "speech_synthesis": 2306, "computer_vision": 2307, "image_classification": 2308, "object_detection": 2309, "semantic_segmentation": 2310, "generative_model": 2311, "discriminative_model": 2312, "diffusion_model": 2313, "variational_autoencoder": 2314, "generative_adversarial": 2315, "contrastive_learning": 2316, "algorithm": 2317, "architecture": 2318, "compute": 2319, "config": 2320, "configuration": 2321, "dimension": 2322, "implement": 2323, "initialize": 2324, "kernel": 2325, "library": 2326, "module": 2327, "normalization": 2328, "objective": 2329, "optimize": 2330, "parameter": 2331, "pipeline": 2332, "preprocess": 2333, "recursive": 2334, "regularize": 2335, "shuffle": 2336, "stride": 2337, "structure": 2338, "tensor": 2339, "transfer": 2340, "transform": 2341, "vectorformula": 2342, "simulation": 2343, "analysis": 2344, "approximation": 2345, "iteration": 2346, "divergence": 2347, "oscillation": 2348, "stability": 2349, "version": 2350, "workspace": 2351, "checkpoint": 2352, "theory": 2353, "observation": 2354, "variable": 2355, "constant": 2356, "function": 2357, "": 2358, "robustness": 2359, "sensitivity": 2360, "specificity": 2361, "correlation": 2362, "regression": 2363, "classification": 2364, "accept": 2365, "achieve": 2366, "adapt": 2367, "adjust": 2368, "admit": 2369, "adopt": 2370, "advance": 2371, "affect": 2372, "apply": 2373, "approach": 2374, "approve": 2375, "arrange": 2376, "assist": 2377, "assume": 2378, "attach": 2379, "attack": 2380, "attempt": 2381, "attend": 2382, "attract": 2383, "avoid": 2384, "beat": 2385, "benefit": 2386, "blame": 2387, "borrow": 2388, "breathe": 2389, "celebrate": 2390, "challenge": 2391, "charge": 2392, "check": 2393, "choose": 2394, "claim": 2395, "clarify": 2396, "collect": 2397, "combine": 2398, "compare": 2399, "compete": 2400, "complain": 2401, "complete": 2402, "confirm": 2403, "connect": 2404, "contain": 2405, "contribute": 2406, "control": 2407, "convince": 2408, "correct": 2409, "cover": 2410, "crash": 2411, "cross": 2412, "damage": 2413, "deal": 2414, "deliver": 2415, "describe": 2416, "design": 2417, "destroy": 2418, "detect": 2419, "determine": 2420, "discover": 2421, "discuss": 2422, "disturb": 2423, "divide": 2424, "draw": 2425, "drop": 2426, "earn": 2427, "employ": 2428, "enable": 2429, "encounter": 2430, "encourage": 2431, "enjoy": 2432, "enter": 2433, "escape": 2434, "examine": 2435, "excite": 2436, "execute": 2437, "exist": 2438, "explore": 2439, "express": 2440, "fail": 2441, "feed": 2442, "fight": 2443, "fill": 2444, "fix": 2445, "fly": 2446, "follow": 2447, "forget": 2448, "form": 2449, "gain": 2450, "hang": 2451, "hide": 2452, "hit": 2453, "hold": 2454, "identify": 2455, "ignore": 2456, "imagine": 2457, "imply": 2458, "improve": 2459, "include": 2460, "increase": 2461, "indicate": 2462, "inform": 2463, "inspire": 2464, "install": 2465, "instruct": 2466, "intend": 2467, "introduce": 2468, "invest": 2469, "invite": 2470, "involve": 2471, "judge": 2472, "jump": 2473, "kick": 2474, "kiss": 2475, "knock": 2476, "laugh": 2477, "launch": 2478, "lay": 2479, "lie": 2480, "lift": 2481, "listen": 2482, "locate": 2483, "manage": 2484, "marry": 2485, "match": 2486, "measure": 2487, "mention": 2488, "miss": 2489, "notice": 2490, "obtain": 2491, "operate": 2492, "order": 2493, "organize": 2494, "participate": 2495, "perform": 2496, "permit": 2497, "plan": 2498, "possess": 2499, "practice": 2500, "prefer": 2501, "prepare": 2502, "present": 2503, "press": 2504, "prevent": 2505, "protect": 2506, "prove": 2507, "provide": 2508, "publish": 2509, "realize": 2510, "receive": 2511, "recognize": 2512, "recommend": 2513, "recover": 2514, "reduce": 2515, "reflect": 2516, "release": 2517, "represent": 2518, "respond": 2519, "rest": 2520, "restore": 2521, "reveal": 2522, "ride": 2523, "ring": 2524, "rise": 2525, "risk": 2526, "roll": 2527, "rush": 2528, "save": 2529, "search": 2530, "select": 2531, "separate": 2532, "share": 2533, "shift": 2534, "shock": 2535, "shoot": 2536, "sign": 2537, "solve": 2538, "spread": 2539, "steal": 2540, "stick": 2541, "store": 2542, "stretch": 2543, "strike": 2544, "succeed": 2545, "suffer": 2546, "supply": 2547, "support": 2548, "suppose": 2549, "surprise": 2550, "survive": 2551, "suspect": 2552, "swim": 2553, "tend": 2554, "touch": 2555, "translate": 2556, "treat": 2557, "trust": 2558, "twist": 2559, "unite": 2560, "view": 2561, "visit": 2562, "vote": 2563, "warn": 2564, "wash": 2565, "wish": 2566, "wonder": 2567, "worry": 2568, "wrap": 2569, "අපේ": 2570, "ඔබේ": 2571, "මගේ": 2572, "ඔවුන්": 2573, "අපි": 2574, "ඔබ": 2575, "මම": 2576, "එතකොට": 2577, "ඊට": 2578, "ඊළඟ": 2579, "පළමු": 2580, "දෙවන": 2581, "තුන්වන": 2582, "එතැන": 2583, "මෙතැන": 2584, "කොතැන": 2585, "කවදා": 2586, "කොහොම": 2587, "ඇයි": 2588, "කොපමණ": 2589, "කීය": 2590, "කොච්චර": 2591, "ඉන්": 2592, "එළියේ": 2593, "ඇතුළේ": 2594, "ඉහළ": 2595, "පහළ": 2596, "පිටත": 2597, "ඇතුළත": 2598, "පහත": 2599, "ඉදිරියේ": 2600, "පිටුපස": 2601, "අයිනේ": 2602, "කිලෝ": 2603, "මීටර්": 2604, "සෙන්ටි": 2605, "හැටියට": 2606, "දැන්": 2607, "ඊයේ": 2608, "අද": 2609, "හෙට": 2610, "අනිද්දා": 2611, "පැය": 2612, "මිනිත්තු": 2613, "තත්පර": 2614, "සතිය": 2615, "මාසය": 2616, "වසර": 2617, "දිනය": 2618, "සමය": 2619, "කාලය": 2620, "හරි": 2621, "නැහැ": 2622, "හොඳ": 2623, "නරක": 2624, "දිග": 2625, "කෙටි": 2626, "උස": 2627, "පළල": 2628, "ගැඹුර": 2629, "බර": 2630, "වේග": 2631, "තරම": 2632, "ප්‍රමාණය": 2633, "සංඛ්‍යාව": 2634, "ගණන": 2635, "අගය": 2636, "සිසු": 2637, "ගුරු": 2638, "ආචාර්ය": 2639, "මහාචාර්ය": 2640, "ප්‍රාධාන": 2641, "උප ප්‍රාධාන": 2642, "සාමාන්‍ය": 2643, "මූලික": 2644, "අතිරේක": 2645, "අමතර": 2646, "එකතු": 2647, "වෙනස්": 2648, "සමාන": 2649, "විවිධ": 2650, "නිශ්චිත": 2651, "අර්ථවත්": 2652, "විධිමත්": 2653, "නිවැරදි": 2654, "පැහැදිලි": 2655, "සරල": 2656, "සංකීර්ණ": 2657, "කරන": 2658, "කරනු": 2659, "කරමින්": 2660, "කරලා": 2661, "යන": 2662, "ගිය": 2663, "ගිහින්": 2664, "එන": 2665, "බලන": 2666, "බැලු": 2667, "ලියන": 2668, "ලියූ": 2669, "කියන": 2670, "කියවන": 2671, "කියූ": 2672, "ඇසුරු": 2673, "භාවිත": 2674, "ගරු": 2675, "කොළඹ": 2676, "කුරුණෑගල": 2677, "මහනුවර": 2678, "ගාල්ල": 2679, "මාතලේ": 2680, "අනුරාධපුර": 2681, "පොළොන්නරුව": 2682, "යාපනය": 2683, "කිලිනොච්චි": 2684, "ත්‍රිකුණාමලය": 2685, "බදුල්ල": 2686, "මොණරාගල": 2687, "මඩකලපුව": 2688, "වෙසක්": 2689, "පොසොන්": 2690, "පුර": 2691, "සිංහ": 2692, "අශ්ව": 2693, "යාන": 2694, "කුස": 2695, "බුද්ධ": 2696, "ධර්ම": 2697, "සංඝ": 2698, "ස්තූතියි": 2699, "කරුණාකර": 2700, "වැඩිදුර": 2701, "කරුණාකරලා": 2702, "ඉක්මනින්": 2703, "හදිසියෙන්": 2704, "ඉතාම": 2705, "ඉතාමත්": 2706, "බොහෝම": 2707, "තරමක්": 2708, "yaml": 2709, "xml": 2710, "csv": 2711, "tsv": 2712, "parquet": 2713, "pdf": 2714, "docx": 2715, "xlsx": 2716, "pptx": 2717, "html": 2718, "css": 2719, "http": 2720, "https": 2721, "ftp": 2722, "ssh": 2723, "ws": 2724, "grpc": 2725, "tcp": 2726, "udp": 2727, "ip": 2728, "dns": 2729, "ssl": 2730, "tls": 2731, "api": 2732, "graphql": 2733, "websocket": 2734, "aws": 2735, "azure": 2736, "gcp": 2737, "docker": 2738, "kubernetes": 2739, "terraform": 2740, "jenkins": 2741, "github": 2742, "gitlab": 2743, "sql": 2744, "nosql": 2745, "mongodb": 2746, "postgresql": 2747, "mysql": 2748, "redis": 2749, "elasticsearch": 2750, "neo4j": 2751, "dynamodb": 2752, "react": 2753, "vue": 2754, "angular": 2755, "fastapi": 2756, "django": 2757, "flask": 2758, "eg": 2759, "ie": 2760, "etc": 2761, "cf": 2762, "vs": 2763, "dr": 2764, "mr": 2765, "prof": 2766, "inc": 2767, "ltd": 2768, "ai": 2769, "ml": 2770, "dl": 2771, "nlp": 2772, "cv": 2773, "rl": 2774, "llm": 2775, "gpu": 2776, "cpu": 2777, "tpu": 2778, "ram": 2779, "ssd": 2780, "sdk": 2781, "cli": 2782, "ide": 2783, "gui": 2784, "ui": 2785, "ux": 2786, "devops": 2787, "kb": 2788, "mb": 2789, "gb": 2790, "tb": 2791, "pb": 2792, "hz": 2793, "khz": 2794, "mhz": 2795, "ghz": 2796, "ms": 2797, "ns": 2798, "eq": 2799, "fig": 2800, "ref": 2801, "thm": 2802, "lem": 2803, "vector": 2804, "scalar": 2805, "norm": 2806, "determinant": 2807, "eigenvalue": 2808, "eigenvector": 2809, "singular": 2810, "orthogonal": 2811, "diagonal": 2812, "rank": 2813, "trace": 2814, "inverse": 2815, "transpose": 2816, "probability": 2817, "statistics": 2818, "distribution": 2819, "gaussian": 2820, "normal": 2821, "bernoulli": 2822, "poisson": 2823, "uniform": 2824, "exponential": 2825, "beta": 2826, "dirichlet": 2827, "bayesian": 2828, "frequentist": 2829, "likelihood": 2830, "posterior": 2831, "prior": 2832, "expectation": 2833, "variance": 2834, "covariance": 2835, "clustering": 2836, "dimensionality": 2837, "pca": 2838, "tsne": 2839, "umap": 2840, "random_forest": 2841, "gradient_boosting": 2842, "xgboost": 2843, "svm": 2844, "knn": 2845, "kmeans": 2846, "dbscan": 2847, "changelog": 2848, "readme": 2849, "license": 2850, "copyright": 2851, "stable": 2852, "experimental": 2853, "deprecated": 2854, "alpha": 2855, "rc": 2856, "note": 2857, "todo": 2858, "fixme": 2859, "hack": 2860, "workaround": 2861, "debug": 2862, "profile": 2863, "benchmark": 2864, "latency": 2865, "throughput": 2866, "bottleneck": 2867, "overhead": 2868, "startup": 2869, "enterprise": 2870, "saas": 2871, "retention_output": 2872, "retention_norm": 2873, "retention_proj": 2874, "retention_gate": 2875, "retention_residual": 2876, "multi_scale_retention": 2877, "scale_1": 2878, "scale_2": 2879, "scale_3": 2880, "scale_4": 2881, "decay_rate": 2882, "chunk_retention": 2883, "chunk_attention": 2884, "recurrent_mode": 2885, "parallel_mode": 2886, "chunkwise_mode": 2887, "hybrid_mode": 2888, "hidden_size": 2889, "num_retention_layers": 2890, "retention_num_heads": 2891, "retention_head_dim": 2892, "ffn_size": 2893, "vocab_size": 2894, "max_seq_len": 2895, "num_groups": 2896, "group_size": 2897, "retention_q_proj": 2898, "retention_k_proj": 2899, "retention_v_proj": 2900, "retention_out_proj": 2901, "retention_gate_proj": 2902, "ffn_up_proj": 2903, "ffn_down_proj": 2904, "embedding_norm": 2905, "final_norm": 2906, "pretrain": 2907, "eval_mode": 2908, "train_mode": 2909, "inference_mode": 2910, "rnn": 2911, "lstm": 2912, "gru": 2913, "linear_transformer": 2914, "kernel_attention": 2915, "state_space_model": 2916, "forward_pass": 2917, "backward_pass": 2918, "hidden_state": 2919, "cell_state": 2920, "memory_state": 2921, "context_states": 2922, "sequence_length": 2923, "tokens_per_second": 2924, "memory_usage": 2925, "compute_cost": 2926, "next_token": 2927, "causal_lm": 2928, "masked_lm": 2929, "cross_entropy_loss": 2930, "label_smoothing": 2931, "warmup_steps": 2932, "total_steps": 2933, "gradient_norm": 2934, "loss_scale": 2935, "save_checkpoint": 2936, "load_checkpoint": 2937, "model_state_dict": 2938, "optimizer_state_dict": 2939, "scaler_state_dict": 2940, "kv_cache": 2941, "past_key_values": 2942, "generate_tokens": 2943, "beam_width": 2944, "max_new_tokens": 2945, "min_new_tokens": 2946, "eval_loss": 2947, "train_loss": 2948, "val_loss": 2949, "learning_curve": 2950, "overfitting": 2951, "underfitting": 2952, "generalization": 2953, "ability": 2954, "absence": 2955, "absorb": 2956, "academy": 2957, "accelerate": 2958, "accessible": 2959, "accomplish": 2960, "account": 2961, "accumulate": 2962, "accurate": 2963, "acknowledge": 2964, "acquire": 2965, "address": 2966, "adequate": 2967, "administration": 2968, "advanced": 2969, "advantage": 2970, "advocate": 2971, "afford": 2972, "agreement": 2973, "allocate": 2974, "alternative": 2975, "ambitious": 2976, "announce": 2977, "annual": 2978, "anticipate": 2979, "apparent": 2980, "appetite": 2981, "applicable": 2982, "appreciate": 2983, "appropriate": 2984, "approval": 2985, "approximate": 2986, "argue": 2987, "argument": 2988, "arise": 2989, "arrangement": 2990, "assess": 2991, "asset": 2992, "assign": 2993, "associate": 2994, "assure": 2995, "atmosphere": 2996, "attribute": 2997, "authority": 2998, "automatic": 2999, "available": 3000, "aware": 3001, "awful": 3002, "background": 3003, "balance": 3004, "barrier": 3005, "basic": 3006, "battle": 3007, "beach": 3008, "bear": 3009, "behalf": 3010, "behavior": 3011, "bitter": 3012, "blanket": 3013, "blind": 3014, "block": 3015, "blood": 3016, "blow": 3017, "board": 3018, "bone": 3019, "border": 3020, "bother": 3021, "bottom": 3022, "boundary": 3023, "bowl": 3024, "brain": 3025, "brand": 3026, "brave": 3027, "bread": 3028, "breath": 3029, "bridge": 3030, "brief": 3031, "bright": 3032, "broad": 3033, "broken": 3034, "brother": 3035, "budget": 3036, "burden": 3037, "burn": 3038, "burst": 3039, "cabinet": 3040, "calm": 3041, "campaign": 3042, "capable": 3043, "capacity": 3044, "captain": 3045, "capture": 3046, "card": 3047, "care": 3048, "career": 3049, "careful": 3050, "carefully": 3051, "catch": 3052, "category": 3053, "cause": 3054, "ceiling": 3055, "central": 3056, "century": 3057, "chair": 3058, "champion": 3059, "championship": 3060, "chance": 3061, "channel": 3062, "chapter": 3063, "characteristic": 3064, "charity": 3065, "chart": 3066, "chase": 3067, "cheap": 3068, "cheese": 3069, "chef": 3070, "chemical": 3071, "chest": 3072, "chicken": 3073, "chief": 3074, "childhood": 3075, "chip": 3076, "cholesterol": 3077, "chosen": 3078, "church": 3079, "cigarette": 3080, "circle": 3081, "circumstance": 3082, "citizen": 3083, "civil": 3084, "clay": 3085, "clever": 3086, "climate": 3087, "climb": 3088, "clinical": 3089, "clock": 3090, "closet": 3091, "clothes": 3092, "club": 3093, "coal": 3094, "coach": 3095, "coalition": 3096, "cognitive": 3097, "collapse": 3098, "colleague": 3099, "collection": 3100, "collective": 3101, "college": 3102, "color": 3103, "column": 3104, "combination": 3105, "comfort": 3106, "comfortable": 3107, "command": 3108, "comment": 3109, "commission": 3110, "commitment": 3111, "committee": 3112, "common": 3113, "communicate": 3114, "communication": 3115, "companion": 3116, "comparison": 3117, "competition": 3118, "competitive": 3119, "competitor": 3120, "complaint": 3121, "complement": 3122, "complex": 3123, "complicated": 3124, "component": 3125, "compose": 3126, "composition": 3127, "comprehensive": 3128, "computer": 3129, "concept": 3130, "concern": 3131, "concerned": 3132, "conclude": 3133, "concrete": 3134, "condition": 3135, "conduct": 3136, "confidence": 3137, "confident": 3138, "confine": 3139, "conflict": 3140, "confuse": 3141, "congress": 3142, "connection": 3143, "conscious": 3144, "consequence": 3145, "conservative": 3146, "considerable": 3147, "consist": 3148, "consistent": 3149, "constantly": 3150, "constitute": 3151, "construct": 3152, "construction": 3153, "consultant": 3154, "consumer": 3155, "consumption": 3156, "contact": 3157, "container": 3158, "contemporary": 3159, "content": 3160, "contest": 3161, "context": 3162, "controversial": 3163, "controversy": 3164, "contribution": 3165, "convenient": 3166, "convention": 3167, "conventional": 3168, "conversation": 3169, "conversion": 3170, "cook": 3171, "cooking": 3172, "cool": 3173, "cooperation": 3174, "core": 3175, "corn": 3176, "corner": 3177, "corporate": 3178, "corporation": 3179, "correspondent": 3180, "cotton": 3181, "couch": 3182, "council": 3183, "counselor": 3184, "county": 3185, "couple": 3186, "courage": 3187, "course": 3188, "court": 3189, "cousin": 3190, "creative": 3191, "creature": 3192, "credit": 3193, "crew": 3194, "crime": 3195, "criminal": 3196, "crisis": 3197, "critic": 3198, "critical": 3199 }, "merges": [] } }