Delete new_gpt_tokenizer

Delete new_gpt_tokenizer directory (duplicate of text_tokenizer/)

new_gpt_tokenizer/added_tokens.json

@@ -1,3 +0,0 @@
-{
-  "<|EOS|>": 1024
-}

new_gpt_tokenizer/merges.txt

@@ -1,768 +0,0 @@
-#version: 0.2
-Ġ t
-h e
-Ġ a
-i n
-Ġt he
-e r
-o n
-Ġ ,
-r e
-Ġ s
-e d
-Ġ o
-Ġ w
-n d
-a t
-Ġ .
-o r
-i t
-Ġ c
-e n
-Ġ f
-i s
-e s
-a r
-Ġo f
-Ġ b
-a n
-Ġ in
-a l
-in g
-Ġ p
-Ġa nd
-a s
-Ġt o
-r o
-i c
-Ġ m
-Ġ d
-Ġ h
-i on
-l e
-o u
-Ġ T
-Ġ re
-Ġ =
-Ġ "
-Ġ A
-Ġ S
-en t
-i l
-Ġt h
-Ġ 1
-s t
-Ġ C
-e l
-o m
-Ġ l
-a m
-Ġ Ċ
-Ġ e
-Ġ n
-Ġ @
-a d
-a c
-Ġw as
-Ġ M
-u r
-ĠT he
-e c
-Ġ on
-l y
-Ġ B
-Ġ I
-Ġ g
-Ġ '
-e t
-o l
-i d
-i v
-i m
-Ġf or
-i r
-- @
-Ġ@ -@
-i g
-o t
-t er
-Ġa s
-Ġ H
-u s
-o w
-Ġs t
-u t
-it h
-a y
-Ġ 2
-Ġ P
-at ion
-v er
-Ġb e
-he r
-Ġth at
-Ġw ith
-Ġ R
-c e
-t h
-Ġ D
-Ġ is
-u n
-e m
-Ġ F
-Ġw h
-u l
-Ġb y
-Ġa l
-c h
-Ġ )
-Ġ (
-Ġ W
-Ġc on
-r a
-Ġ G
-o s
-Ġ L
-Ġ N
-Ġa t
-er s
-c t
-Ġ it
-Ġ1 9
-ro m
-a nd
-Ġa n
-u m
-es t
-Ġ J
-a g
-Ġ he
-0 0
-is t
-a in
-o d
-a v
-r i
-Ġ E
-Ġ O
-Ġf rom
-Ġc om
-Ġh is
-o p
-Ġp ro
-re s
-i es
-i f
-Ġ v
-or t
-er e
-il l
-l d
-Ġd e
-p p
-Ġs u
-o re
-ĠI n
-Ġ r
-Ġs e
-Ġw ere
-e w
-on g
-ig h
-ar d
-at e
-al l
-ar t
-a k
-ic h
-Ġc h
-Ġo r
-a b
-an t
-u d
-o c
-b er
-Ġe x
-g h
-it y
-at ed
-p t
-es s
-e ar
-Ġ K
-Ġp l
-am e
-q u
-iv e
-ro u
-Ġa re
-Ġ â
-Ġs h
-Ġ k
-ac k
-ec t
-Ġâ Ģ
-Ġ U
-Ġh ad
-s e
-Ġwh ich
-re d
-o v
-ĠS t
-as t
-Ġs p
-i an
-Ġ y
-m ent
-Ġ le
-Ġn ot
-g e
-or d
-r it
-i p
-in e
-el l
-al ly
-ou r
-o st
-igh t
-t her
-a p
-Ġ u
-is h
-ĠC h
-ou n
-i a
-Ġ 3
-av e
-ar y
-u st
-o g
-Ġ2 00
-Ġ un
-ou s
-ir st
-Ġ V
-c c
-Ġin c
-Ġ ;
-Ġcom p
-r u
-ion s
-Ġthe ir
-Ġb ut
-id e
-u re
-s o
-Ġcon t
-Ġin t
-f ter
-ic al
-i al
-Ġa r
-Ġf irst
-ou ld
-Ġit s
-he d
-ĠâĢ ĵ
-Ġw he
-w o
-ou t
-u b
-Ġ2 0
-f f
-Ġ :
-u e
-Ġ her
-ow n
-o k
-Ġal so
-Ġc l
-p er
-ig n
-at er
-r an
-or m
-i e
-om e
-or k
-as s
-i re
-e nd
-Ġre s
-Ġa b
-Ġa d
-Ġ us
-r y
-Ġre c
-Ġh ave
-ag e
-ĠH e
-Ġ 4
-Ġ ro
-m er
-Ġon e
-on d
-l ow
-Ġh as
-ĠT h
-d u
-Ġ 5
-Ġp er
-Ġbe en
-im e
-Ġt wo
-en ce
-l and
-Ġ1 8
-. @
-Ġ@ .@
-ul t
-re e
-ou gh
-i le
-Ġwh o
-ĠA l
-Ġs c
-ur ing
-p l
-or y
-it ion
-r ic
-ation s
-Ġd is
-Ġth is
-Ġb ec
-Ġa pp
-i z
-ĠI t
-a re
-ac h
-l ud
-ad e
-Ġpl ay
-Ġ j
-Ġm an
-ac t
-el y
-Ġp art
-Ġd es
-Ġa g
-Ġthe y
-Ġy ear
-oun t
-Ġ20 1
-Ġo ver
-Ġo ther
-ou nd
-Ġa fter
-i b
-o ver
-Ġs er
-Ġ en
-Ġof f
-Ġ im
-ct ion
-Ġ Y
-k e
-it e
-, @
-Ġ@ ,@
-t e
-ur n
-Ġinc lud
-res s
-an ce
-an g
-Ġat t
-ic e
-ac e
-ar k
-Ġo ut
-w n
-p h
-em ber
-Ġp re
-Ġu p
-en s
-m an
-Ġe v
-Ġt ime
-nd er
-rou gh
-c ed
-Ġf in
-Ġint o
-on e
-p ort
-rou nd
-w e
-re n
-l es
-in t
-ĠO n
-v el
-Ġcom m
-Ġs he
-as on
-am p
-Ġt e
-Ġw ould
-w ard
-Ġm ore
-Ġ 6
-i ed
-os e
-ri b
-ĠU n
-Ġal l
-ing s
-ter n
-c es
-ab le
-Ġw e
-it ed
-e ver
-ent s
-Ġh im
-as ed
-or s
-o y
-o od
-Ġc ent
-i x
-as e
-il d
-ĠA n
-Ġ 7
-Ġw ork
-at es
-i ous
-at h
-Ġp o
-ro p
-ol d
-al s
-is s
-e y
-ic t
-Ġf e
-Ġthe m
-g an
-Ġs ec
-Ġb et
-Ġwhe n
-Ġs ong
-Ġre m
-e p
-f orm
-a il
-f er
-Ġe ar
-ub l
-a w
-Ġk n
-ak e
-a us
-Ġm ost
-Ġcon s
-Ġd uring
-ĠA s
-or th
-Ġn ew
-er ed
-il m
-v ed
-at t
-Ġon ly
-Ġ 9
-Ġd ec
-Ġ 8
-ic k
-Ġg ame
-on s
-u g
-Ġt r
-f t
-ot h
-o ok
-ĠM ar
-re at
-w ay
-Ġc an
-ol low
-ou th
-we en
-ĠE n
-Ġ19 9
-ter s
-Ġre l
-in d
-Ġab out
-Ġse ason
-Ġag ain
-r al
-Ġth ree
-ation al
-Ġu nder
-ul ar
-Ġm e
-Ġth an
-ĠC om
-ĠA r
-h ip
-o b
-Ġn e
-Ġbet ween
-Ġf l
-h n
-v e
-Ġch ar
-Ġc ol
-Ġrec ord
-i ew
-r on
-f ore
-Ġth rough
-is ion
-or n
-Ġ 00
-oc k
-Ġ ver
-Ġl ater
-Ġn um
-Ġe nd
-ol og
-am es
-Ġp os
-Ġw rit
-Ġpro du
-Ġwh ile
-Ġa ct
-Ġre le
-Ġf ilm
-is hed
-Ġp r
-an s
-Ġre g
-Ġfor m
-Ġas s
-ĠS e
-ur y
-t ed
-t s
-Ġm ade
-Ġsu b
-Ġp e
-Ġs o
-or ld
-Ġre t
-ĠN ew
-Ġsp ec
-Ġa cc
-Ġ qu
-Ġwhe re
-en er
-Ġm ov
-he s
-mer ic
-at ing
-Ġin ter
-ĠL e
-ĠA meric
-Ġ ra
-Ġs ome
-Ġc o
-Ġl ar
-Ġb u
-Ġde f
-b um
-Ġa c
-Ġm us
-Ġf ollow
-ĠA t
-in s
-iv ed
-if ic
-u al
-Ġa m
-Ġsu ch
-Ġsec ond
-i ke
-Ġf our
-Ġin d
-an n
-he n
-Ġus ed
-ĠR e
-ic s
-le ct
-Ġd ay
-i el
-il y
-ĠTh is
-Ġ 0
-Ġp ubl
-Ġc all
-ĠJ o
-l l
-Ġal bum
-Ġ00 0
-ran s
-Ġd o
-an y
-Ġbe fore
-ro s
-ĠS h
-Ġs y
-a id
-ĠEn g
-Ġbe ing
-Ġ1 0
-u c
-Ġe p
-Ġsu pp
-Ġthe re
-Ġyear s
-ar s
-ow ever
-Ġ ent
-if e
-Ġh igh
-Ġf ound
-ir d
-Ġn o
-Ġs et
-in es
-iv er
-i o
-ot her
-j ect
-Ġs ur
-a j
-t en
-Ġt ra
-Ġ1 2
-is ed
-it ies
-vel op
-Ġb l
-al e
-Ġser ies
-Ġl oc
-Ġnum ber
-Ġp res
-an e
-aus e
-od e
-e k
-t on
-ĠS c
-i er
-is e
-Ġse ver
-in ce
-Ġb oth
-an k
-ro w
-ire ct
-s on
-Ġthe n
-ĠB rit
-i et
-Ġ1 6
-Ġep is
-Ġinclud ing
-it s
-ig in
-p r
-Ġ /
-Ġagain st
-Ġw ell
-Ġbec ame
-Ġex p
-Ġkn own
-Ġt rans
-Ġchar ac
-ĠâĢ Ķ
-r am
-Ġb ack
-Ġad d
-Ġp op
-Ġg o
-ur ch
-Ġdes c
-Ġs ing
-iel d
-Ġper form
-ain ed
-Ġre ce
-id ent
-Ġe m
-er t
-u res
-Ġin v
-Ġde p
-Ġ19 8
-a ir
-er n
-at her
-f ul
-Ġ Z
-Ġm on
-Ġman y
-Ġm ain
-Ġst ud
-Ġl ong
-in n
-th ough
-u p
-o ol
-ĠUn ited
-l ed
-em ent
-Ġ1 5
-ow er
-ĠJo hn
-Ġo p
-Ġ1 1
-in ed
-Ġm et
-o ber
-le y
-Ġ1 7
-Ġcent ury
-Ġte am
-Ġ est
-ĠA fter
-y l
-Ġm in
-u ch
-ut e
-Ġde velop
-ĠS he
-i am
-Ġsh ow
-el f
-Ġre p
-Ġcon c
-at ive
-Ġc re
-over n
-a red
-Ġ19 4
-Ġor igin
-Ġs m
-iv ers
-a z
-Ġle ad
-Ġsever al
-a h
-Ġo b
-Ġre v
-Ġm ill
-er m
-u ally
-o ot
-Ġbe gan
-Ġ19 6

new_gpt_tokenizer/special_tokens_map.json

@@ -1,5 +0,0 @@
-{
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|EOS|>",
-  "unk_token": "<|endoftext|>"
-}

new_gpt_tokenizer/tokenizer_config.json

@@ -1,34 +0,0 @@
-{
-  "add_bos_token": false,
-  "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "errors": "replace",
-  "model_max_length": 512,
-  "name_or_path": "models/clip_caption_model",
-  "pad_token": null,
-  "special_tokens_map_file": null,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}

new_gpt_tokenizer/vocab.json

@@ -1,1026 +0,0 @@
-{
-  "!": 1,
-  "\"": 2,
-  "#": 3,
-  "$": 4,
-  "%": 5,
-  "&": 6,
-  "'": 7,
-  "(": 8,
-  ")": 9,
-  "*": 10,
-  "+": 11,
-  ",": 12,
-  ",@": 624,
-  "-": 13,
-  "-@": 339,
-  ".": 14,
-  ".@": 573,
-  "/": 15,
-  "0": 16,
-  "00": 395,
-  "1": 17,
-  "2": 18,
-  "3": 19,
-  "4": 20,
-  "5": 21,
-  "6": 22,
-  "7": 23,
-  "8": 24,
-  "9": 25,
-  ":": 26,
-  ";": 27,
-  "<": 28,
-  "<|endoftext|>": 0,
-  "=": 29,
-  ">": 30,
-  "?": 31,
-  "@": 32,
-  "A": 33,
-  "B": 34,
-  "C": 35,
-  "D": 36,
-  "E": 37,
-  "F": 38,
-  "G": 39,
-  "H": 40,
-  "I": 41,
-  "J": 42,
-  "K": 43,
-  "L": 44,
-  "M": 45,
-  "N": 46,
-  "O": 47,
-  "P": 48,
-  "Q": 49,
-  "R": 50,
-  "S": 51,
-  "T": 52,
-  "U": 53,
-  "V": 54,
-  "W": 55,
-  "X": 56,
-  "Y": 57,
-  "Z": 58,
-  "[": 59,
-  "\\": 60,
-  "]": 61,
-  "^": 62,
-  "_": 63,
-  "`": 64,
-  "a": 65,
-  "ab": 435,
-  "able": 677,
-  "ac": 320,
-  "ace": 634,
-  "ach": 595,
-  "ack": 457,
-  "act": 601,
-  "ad": 319,
-  "ade": 597,
-  "ag": 393,
-  "age": 554,
-  "ah": 1015,
-  "aid": 873,
-  "ail": 714,
-  "ain": 397,
-  "ained": 953,
-  "air": 962,
-  "aj": 897,
-  "ak": 431,
-  "ake": 720,
-  "al": 285,
-  "ale": 905,
-  "all": 429,
-  "ally": 480,
-  "als": 700,
-  "am": 314,
-  "ame": 449,
-  "ames": 791,
-  "amp": 663,
-  "an": 283,
-  "ance": 630,
-  "and": 388,
-  "ane": 910,
-  "ang": 631,
-  "ank": 921,
-  "ann": 849,
-  "ans": 801,
-  "ant": 436,
-  "any": 868,
-  "ap": 485,
-  "ar": 280,
-  "ard": 427,
-  "are": 594,
-  "ared": 1007,
-  "ark": 635,
-  "ars": 882,
-  "art": 430,
-  "ary": 493,
-  "as": 289,
-  "ase": 689,
-  "ased": 683,
-  "ason": 662,
-  "ass": 544,
-  "ast": 467,
-  "at": 271,
-  "ate": 428,
-  "ated": 443,
-  "ater": 538,
-  "ates": 694,
-  "ath": 696,
-  "ather": 964,
-  "ating": 824,
-  "ation": 354,
-  "ational": 761,
-  "ations": 587,
-  "ative": 1004,
-  "att": 731,
-  "aus": 721,
-  "ause": 911,
-  "av": 399,
-  "ave": 492,
-  "aw": 718,
-  "ay": 351,
-  "az": 1012,
-  "b": 66,
-  "ber": 439,
-  "bum": 834,
-  "c": 67,
-  "cc": 501,
-  "ce": 361,
-  "ced": 648,
-  "ces": 676,
-  "ch": 372,
-  "ct": 384,
-  "ction": 620,
-  "d": 68,
-  "du": 564,
-  "e": 69,
-  "ear": 446,
-  "ec": 325,
-  "ect": 458,
-  "ed": 267,
-  "ek": 913,
-  "el": 311,
-  "elf": 1001,
-  "ell": 479,
-  "ely": 602,
-  "em": 366,
-  "ember": 639,
-  "ement": 978,
-  "en": 276,
-  "ence": 570,
-  "end": 546,
-  "ener": 820,
-  "ens": 642,
-  "ent": 305,
-  "ents": 681,
-  "ep": 712,
-  "er": 262,
-  "ere": 413,
-  "ered": 728,
-  "erm": 1019,
-  "ern": 963,
-  "ers": 383,
-  "ert": 957,
-  "es": 279,
-  "ess": 445,
-  "est": 391,
-  "et": 332,
-  "ever": 680,
-  "ew": 424,
-  "ey": 702,
-  "f": 70,
-  "fer": 715,
-  "ff": 528,
-  "fore": 780,
-  "form": 713,
-  "ft": 741,
-  "fter": 514,
-  "ful": 965,
-  "g": 71,
-  "gan": 706,
-  "ge": 474,
-  "gh": 441,
-  "h": 72,
-  "he": 258,
-  "hed": 521,
-  "hen": 850,
-  "her": 357,
-  "hes": 822,
-  "hip": 768,
-  "hn": 773,
-  "i": 73,
-  "ia": 490,
-  "ial": 516,
-  "iam": 999,
-  "ian": 469,
-  "ib": 614,
-  "ic": 292,
-  "ical": 515,
-  "ice": 633,
-  "ich": 432,
-  "ick": 736,
-  "ics": 853,
-  "ict": 703,
-  "id": 334,
-  "ide": 509,
-  "ident": 955,
-  "ie": 541,
-  "ied": 669,
-  "iel": 856,
-  "ield": 951,
-  "ier": 916,
-  "ies": 409,
-  "iet": 927,
-  "iew": 778,
-  "if": 410,
-  "ife": 885,
-  "ific": 841,
-  "ig": 341,
-  "igh": 426,
-  "ight": 483,
-  "igin": 932,
-  "ign": 537,
-  "ike": 846,
-  "il": 306,
-  "ild": 690,
-  "ile": 578,
-  "ill": 414,
-  "ilm": 729,
-  "ily": 857,
-  "im": 336,
-  "ime": 568,
-  "in": 260,
-  "ince": 919,
-  "ind": 755,
-  "ine": 478,
-  "ined": 984,
-  "ines": 891,
-  "ing": 286,
-  "ings": 674,
-  "inn": 972,
-  "ins": 839,
-  "int": 657,
-  "io": 893,
-  "ion": 296,
-  "ions": 506,
-  "ious": 695,
-  "ip": 477,
-  "ir": 338,
-  "ird": 888,
-  "ire": 545,
-  "irect": 923,
-  "irst": 499,
-  "is": 278,
-  "ise": 917,
-  "ised": 901,
-  "ish": 487,
-  "ished": 799,
-  "ision": 782,
-  "iss": 701,
-  "ist": 396,
-  "it": 274,
-  "ite": 623,
-  "ited": 679,
-  "ith": 350,
-  "ities": 902,
-  "ition": 585,
-  "its": 931,
-  "ity": 442,
-  "iv": 335,
-  "ive": 451,
-  "ived": 840,
-  "iver": 892,
-  "ivers": 1011,
-  "ix": 688,
-  "iz": 592,
-  "j": 74,
-  "ject": 895,
-  "k": 75,
-  "ke": 622,
-  "l": 76,
-  "land": 571,
-  "ld": 415,
-  "le": 297,
-  "lect": 854,
-  "led": 977,
-  "les": 656,
-  "ley": 987,
-  "ll": 863,
-  "low": 561,
-  "lud": 596,
-  "ly": 327,
-  "m": 77,
-  "man": 643,
-  "ment": 471,
-  "mer": 558,
-  "meric": 823,
-  "n": 78,
-  "nd": 270,
-  "nder": 646,
-  "o": 79,
-  "ob": 769,
-  "ober": 986,
-  "oc": 438,
-  "ock": 785,
-  "od": 398,
-  "ode": 912,
-  "og": 495,
-  "ok": 533,
-  "ol": 333,
-  "old": 699,
-  "ollow": 748,
-  "olog": 790,
-  "om": 312,
-  "ome": 542,
-  "on": 263,
-  "ond": 560,
-  "one": 651,
-  "ong": 425,
-  "ons": 738,
-  "ood": 686,
-  "ook": 743,
-  "ool": 975,
-  "oot": 1021,
-  "op": 406,
-  "or": 273,
-  "ord": 475,
-  "ore": 419,
-  "ork": 543,
-  "orld": 813,
-  "orm": 540,
-  "orn": 783,
-  "ors": 684,
-  "ort": 412,
-  "orth": 726,
-  "ory": 584,
-  "os": 379,
-  "ose": 670,
-  "ost": 482,
-  "ot": 342,
-  "oth": 742,
-  "other": 894,
-  "ou": 298,
-  "ough": 577,
-  "ould": 519,
-  "oun": 489,
-  "ound": 612,
-  "ount": 608,
-  "our": 481,
-  "ous": 498,
-  "out": 525,
-  "outh": 749,
-  "ov": 465,
-  "over": 615,
-  "overn": 1006,
-  "ow": 347,
-  "ower": 980,
-  "owever": 883,
-  "own": 532,
-  "oy": 685,
-  "p": 80,
-  "per": 536,
-  "ph": 638,
-  "pl": 583,
-  "port": 652,
-  "pp": 417,
-  "pr": 933,
-  "pt": 444,
-  "q": 81,
-  "qu": 450,
-  "r": 82,
-  "ra": 377,
-  "ral": 759,
-  "ram": 943,
-  "ran": 539,
-  "rans": 866,
-  "re": 265,
-  "reat": 745,
-  "red": 464,
-  "ree": 576,
-  "ren": 655,
-  "res": 408,
-  "ress": 629,
-  "ri": 400,
-  "rib": 671,
-  "ric": 586,
-  "rit": 476,
-  "ro": 291,
-  "rom": 387,
-  "ron": 779,
-  "rop": 698,
-  "ros": 870,
-  "rou": 452,
-  "rough": 647,
-  "round": 653,
-  "row": 922,
-  "ru": 505,
-  "ry": 551,
-  "s": 83,
-  "se": 462,
-  "so": 511,
-  "son": 924,
-  "st": 309,
-  "t": 84,
-  "te": 626,
-  "ted": 807,
-  "ten": 898,
-  "ter": 343,
-  "tern": 675,
-  "ters": 753,
-  "th": 362,
-  "ther": 484,
-  "though": 973,
-  "ton": 914,
-  "ts": 808,
-  "u": 85,
-  "ual": 842,
-  "ually": 1020,
-  "ub": 526,
-  "ubl": 717,
-  "uc": 877,
-  "uch": 995,
-  "ud": 437,
-  "ue": 530,
-  "ug": 739,
-  "ul": 369,
-  "ular": 763,
-  "ult": 575,
-  "um": 390,
-  "un": 365,
-  "up": 974,
-  "ur": 323,
-  "urch": 948,
-  "ure": 510,
-  "ures": 958,
-  "uring": 582,
-  "urn": 627,
-  "ury": 806,
-  "us": 346,
-  "ust": 494,
-  "ut": 349,
-  "ute": 996,
-  "v": 86,
-  "ve": 774,
-  "ved": 730,
-  "vel": 659,
-  "velop": 903,
-  "ver": 355,
-  "w": 87,
-  "ward": 666,
-  "way": 746,
-  "we": 654,
-  "ween": 750,
-  "wn": 637,
-  "wo": 524,
-  "x": 88,
-  "y": 89,
-  "yl": 993,
-  "z": 90,
-  "{": 91,
-  "|": 92,
-  "}": 93,
-  "~": 94,
-  "¡": 95,
-  "¢": 96,
-  "£": 97,
-  "¤": 98,
-  "¥": 99,
-  "¦": 100,
-  "§": 101,
-  "¨": 102,
-  "©": 103,
-  "ª": 104,
-  "«": 105,
-  "¬": 106,
-  "®": 107,
-  "¯": 108,
-  "°": 109,
-  "±": 110,
-  "²": 111,
-  "³": 112,
-  "´": 113,
-  "µ": 114,
-  "¶": 115,
-  "·": 116,
-  "¸": 117,
-  "¹": 118,
-  "º": 119,
-  "»": 120,
-  "¼": 121,
-  "½": 122,
-  "¾": 123,
-  "¿": 124,
-  "À": 125,
-  "Á": 126,
-  "Â": 127,
-  "Ã": 128,
-  "Ä": 129,
-  "Å": 130,
-  "Æ": 131,
-  "Ç": 132,
-  "È": 133,
-  "É": 134,
-  "Ê": 135,
-  "Ë": 136,
-  "Ì": 137,
-  "Í": 138,
-  "Î": 139,
-  "Ï": 140,
-  "Ð": 141,
-  "Ñ": 142,
-  "Ò": 143,
-  "Ó": 144,
-  "Ô": 145,
-  "Õ": 146,
-  "Ö": 147,
-  "×": 148,
-  "Ø": 149,
-  "Ù": 150,
-  "Ú": 151,
-  "Û": 152,
-  "Ü": 153,
-  "Ý": 154,
-  "Þ": 155,
-  "ß": 156,
-  "à": 157,
-  "á": 158,
-  "â": 159,
-  "ã": 160,
-  "ä": 161,
-  "å": 162,
-  "æ": 163,
-  "ç": 164,
-  "è": 165,
-  "é": 166,
-  "ê": 167,
-  "ë": 168,
-  "ì": 169,
-  "í": 170,
-  "î": 171,
-  "ï": 172,
-  "ð": 173,
-  "ñ": 174,
-  "ò": 175,
-  "ó": 176,
-  "ô": 177,
-  "õ": 178,
-  "ö": 179,
-  "÷": 180,
-  "ø": 181,
-  "ù": 182,
-  "ú": 183,
-  "û": 184,
-  "ü": 185,
-  "ý": 186,
-  "þ": 187,
-  "ÿ": 188,
-  "Ā": 189,
-  "ā": 190,
-  "Ă": 191,
-  "ă": 192,
-  "Ą": 193,
-  "ą": 194,
-  "Ć": 195,
-  "ć": 196,
-  "Ĉ": 197,
-  "ĉ": 198,
-  "Ċ": 199,
-  "ċ": 200,
-  "Č": 201,
-  "č": 202,
-  "Ď": 203,
-  "ď": 204,
-  "Đ": 205,
-  "đ": 206,
-  "Ē": 207,
-  "ē": 208,
-  "Ĕ": 209,
-  "ĕ": 210,
-  "Ė": 211,
-  "ė": 212,
-  "Ę": 213,
-  "ę": 214,
-  "Ě": 215,
-  "ě": 216,
-  "Ĝ": 217,
-  "ĝ": 218,
-  "Ğ": 219,
-  "ğ": 220,
-  "Ġ": 221,
-  "Ġ\"": 302,
-  "Ġ'": 331,
-  "Ġ(": 374,
-  "Ġ)": 373,
-  "Ġ,": 264,
-  "Ġ.": 272,
-  "Ġ/": 934,
-  "Ġ0": 859,
-  "Ġ00": 784,
-  "Ġ000": 865,
-  "Ġ1": 308,
-  "Ġ10": 876,
-  "Ġ11": 983,
-  "Ġ12": 900,
-  "Ġ15": 979,
-  "Ġ16": 928,
-  "Ġ17": 988,
-  "Ġ18": 572,
-  "Ġ19": 386,
-  "Ġ194": 1008,
-  "Ġ196": 1023,
-  "Ġ198": 961,
-  "Ġ199": 752,
-  "Ġ2": 352,
-  "Ġ20": 527,
-  "Ġ200": 496,
-  "Ġ201": 609,
-  "Ġ3": 491,
-  "Ġ4": 556,
-  "Ġ5": 565,
-  "Ġ6": 668,
-  "Ġ7": 692,
-  "Ġ8": 735,
-  "Ġ9": 733,
-  "Ġ:": 529,
-  "Ġ;": 503,
-  "Ġ=": 301,
-  "Ġ@": 318,
-  "Ġ@,@": 625,
-  "Ġ@-@": 340,
-  "Ġ@.@": 574,
-  "ĠA": 303,
-  "ĠAfter": 992,
-  "ĠAl": 580,
-  "ĠAmeric": 827,
-  "ĠAn": 691,
-  "ĠAr": 767,
-  "ĠAs": 725,
-  "ĠAt": 838,
-  "ĠB": 328,
-  "ĠBrit": 926,
-  "ĠC": 310,
-  "ĠCh": 488,
-  "ĠCom": 766,
-  "ĠD": 363,
-  "ĠE": 401,
-  "ĠEn": 751,
-  "ĠEng": 874,
-  "ĠF": 367,
-  "ĠG": 378,
-  "ĠH": 345,
-  "ĠHe": 555,
-  "ĠI": 329,
-  "ĠIn": 420,
-  "ĠIt": 593,
-  "ĠJ": 392,
-  "ĠJo": 862,
-  "ĠJohn": 981,
-  "ĠK": 447,
-  "ĠL": 380,
-  "ĠLe": 826,
-  "ĠM": 322,
-  "ĠMar": 744,
-  "ĠN": 381,
-  "ĠNew": 815,
-  "ĠO": 402,
-  "ĠOn": 658,
-  "ĠP": 353,
-  "ĠR": 360,
-  "ĠRe": 852,
-  "ĠS": 304,
-  "ĠSc": 915,
-  "ĠSe": 805,
-  "ĠSh": 871,
-  "ĠShe": 998,
-  "ĠSt": 466,
-  "ĠT": 299,
-  "ĠTh": 563,
-  "ĠThe": 324,
-  "ĠThis": 858,
-  "ĠU": 460,
-  "��Un": 672,
-  "ĠUnited": 976,
-  "ĠV": 500,
-  "ĠW": 375,
-  "ĠY": 621,
-  "ĠZ": 966,
-  "Ġa": 259,
-  "Ġab": 548,
-  "Ġabout": 756,
-  "Ġac": 835,
-  "Ġacc": 817,
-  "Ġact": 796,
-  "Ġad": 549,
-  "Ġadd": 945,
-  "Ġafter": 613,
-  "Ġag": 605,
-  "Ġagain": 758,
-  "Ġagainst": 935,
-  "Ġal": 371,
-  "Ġalbum": 864,
-  "Ġall": 673,
-  "Ġalso": 534,
-  "Ġam": 843,
-  "Ġan": 389,
-  "Ġand": 288,
-  "Ġapp": 591,
-  "Ġar": 517,
-  "Ġare": 453,
-  "Ġas": 344,
-  "Ġass": 804,
-  "Ġat": 382,
-  "Ġatt": 632,
-  "Ġb": 282,
-  "Ġback": 944,
-  "Ġbe": 356,
-  "Ġbec": 590,
-  "Ġbecame": 937,
-  "Ġbeen": 567,
-  "Ġbefore": 869,
-  "Ġbegan": 1022,
-  "Ġbeing": 875,
-  "Ġbet": 708,
-  "Ġbetween": 771,
-  "Ġbl": 904,
-  "Ġboth": 920,
-  "Ġbu": 832,
-  "Ġbut": 508,
-  "Ġby": 370,
-  "Ġc": 275,
-  "Ġcall": 861,
-  "Ġcan": 747,
-  "Ġcent": 687,
-  "Ġcentury": 989,
-  "Ġch": 433,
-  "Ġchar": 775,
-  "Ġcharac": 941,
-  "Ġcl": 535,
-  "Ġco": 830,
-  "Ġcol": 776,
-  "Ġcom": 404,
-  "Ġcomm": 660,
-  "Ġcomp": 504,
-  "Ġcon": 376,
-  "Ġconc": 1003,
-  "Ġcons": 723,
-  "Ġcont": 512,
-  "Ġcre": 1005,
-  "Ġd": 294,
-  "Ġday": 855,
-  "Ġde": 416,
-  "Ġdec": 734,
-  "Ġdef": 833,
-  "Ġdep": 960,
-  "Ġdes": 604,
-  "Ġdesc": 949,
-  "Ġdevelop": 997,
-  "Ġdis": 588,
-  "Ġdo": 867,
-  "Ġduring": 724,
-  "Ġe": 316,
-  "Ġear": 716,
-  "Ġem": 956,
-  "Ġen": 617,
-  "Ġend": 789,
-  "Ġent": 884,
-  "Ġep": 878,
-  "Ġepis": 929,
-  "Ġest": 991,
-  "Ġev": 644,
-  "Ġex": 440,
-  "Ġexp": 938,
-  "Ġf": 277,
-  "Ġfe": 704,
-  "Ġfilm": 798,
-  "Ġfin": 649,
-  "Ġfirst": 518,
-  "Ġfl": 772,
-  "Ġfollow": 837,
-  "Ġfor": 337,
-  "Ġform": 803,
-  "Ġfound": 887,
-  "Ġfour": 847,
-  "Ġfrom": 403,
-  "Ġg": 330,
-  "Ġgame": 737,
-  "Ġgo": 947,
-  "Ġh": 295,
-  "Ġhad": 461,
-  "Ġhas": 562,
-  "Ġhave": 553,
-  "Ġhe": 394,
-  "Ġher": 531,
-  "Ġhigh": 886,
-  "Ġhim": 682,
-  "Ġhis": 405,
-  "Ġim": 619,
-  "Ġin": 284,
-  "Ġinc": 502,
-  "Ġinclud": 628,
-  "Ġincluding": 930,
-  "Ġind": 848,
-  "Ġint": 513,
-  "Ġinter": 825,
-  "Ġinto": 650,
-  "Ġinv": 959,
-  "Ġis": 364,
-  "Ġit": 385,
-  "Ġits": 520,
-  "Ġj": 599,
-  "Ġk": 456,
-  "Ġkn": 719,
-  "Ġknown": 939,
-  "Ġl": 313,
-  "Ġlar": 831,
-  "Ġlater": 787,
-  "Ġle": 472,
-  "Ġlead": 1013,
-  "Ġloc": 907,
-  "Ġlong": 971,
-  "Ġm": 293,
-  "Ġmade": 809,
-  "Ġmain": 969,
-  "Ġman": 600,
-  "Ġmany": 968,
-  "Ġme": 764,
-  "Ġmet": 985,
-  "Ġmill": 1018,
-  "Ġmin": 994,
-  "Ġmon": 967,
-  "Ġmore": 667,
-  "Ġmost": 722,
-  "Ġmov": 821,
-  "Ġmus": 836,
-  "Ġn": 317,
-  "Ġne": 770,
-  "Ġnew": 727,
-  "Ġno": 889,
-  "Ġnot": 473,
-  "Ġnum": 788,
-  "Ġnumber": 908,
-  "Ġo": 268,
-  "Ġob": 1016,
-  "Ġof": 281,
-  "Ġoff": 618,
-  "Ġon": 326,
-  "Ġone": 559,
-  "Ġonly": 732,
-  "Ġop": 982,
-  "Ġor": 434,
-  "Ġorigin": 1009,
-  "Ġother": 611,
-  "Ġout": 636,
-  "Ġover": 610,
-  "Ġp": 287,
-  "Ġpart": 603,
-  "Ġpe": 811,
-  "Ġper": 566,
-  "Ġperform": 952,
-  "Ġpl": 448,
-  "Ġplay": 598,
-  "Ġpo": 697,
-  "Ġpop": 946,
-  "Ġpos": 792,
-  "Ġpr": 800,
-  "Ġpre": 640,
-  "Ġpres": 909,
-  "Ġpro": 407,
-  "Ġprodu": 794,
-  "Ġpubl": 860,
-  "Ġqu": 818,
-  "Ġr": 421,
-  "Ġra": 828,
-  "Ġre": 300,
-  "Ġrec": 552,
-  "Ġrece": 954,
-  "Ġrecord": 777,
-  "Ġreg": 802,
-  "Ġrel": 754,
-  "Ġrele": 797,
-  "Ġrem": 711,
-  "Ġrep": 1002,
-  "Ġres": 547,
-  "Ġret": 814,
-  "Ġrev": 1017,
-  "Ġro": 557,
-  "Ġs": 266,
-  "Ġsc": 581,
-  "Ġse": 422,
-  "Ġseason": 757,
-  "Ġsec": 707,
-  "Ġsecond": 845,
-  "Ġser": 616,
-  "Ġseries": 906,
-  "Ġset": 890,
-  "Ġsever": 918,
-  "Ġseveral": 1014,
-  "Ġsh": 455,
-  "Ġshe": 661,
-  "Ġshow": 1000,
-  "Ġsing": 950,
-  "Ġsm": 1010,
-  "Ġso": 812,
-  "Ġsome": 829,
-  "Ġsong": 710,
-  "Ġsp": 468,
-  "Ġspec": 816,
-  "Ġst": 348,
-  "Ġstud": 970,
-  "Ġsu": 418,
-  "Ġsub": 810,
-  "Ġsuch": 844,
-  "Ġsupp": 879,
-  "Ġsur": 896,
-  "Ġsy": 872,
-  "Ġt": 257,
-  "Ġte": 664,
-  "Ġteam": 990,
-  "Ġth": 307,
-  "Ġthan": 765,
-  "Ġthat": 358,
-  "Ġthe": 261,
-  "Ġtheir": 507,
-  "Ġthem": 705,
-  "Ġthen": 925,
-  "Ġthere": 880,
-  "Ġthey": 606,
-  "Ġthis": 589,
-  "Ġthree": 760,
-  "Ġthrough": 781,
-  "Ġtime": 645,
-  "Ġto": 290,
-  "Ġtr": 740,
-  "Ġtra": 899,
-  "Ġtrans": 940,
-  "Ġtwo": 569,
-  "Ġu": 486,
-  "Ġun": 497,
-  "Ġunder": 762,
-  "Ġup": 641,
-  "Ġus": 550,
-  "Ġused": 851,
-  "Ġv": 411,
-  "Ġver": 786,
-  "Ġw": 269,
-  "Ġwas": 321,
-  "Ġwe": 678,
-  "Ġwell": 936,
-  "Ġwere": 423,
-  "Ġwh": 368,
-  "Ġwhe": 523,
-  "Ġwhen": 709,
-  "Ġwhere": 819,
-  "Ġwhich": 463,
-  "Ġwhile": 795,
-  "Ġwho": 579,
-  "Ġwith": 359,
-  "Ġwork": 693,
-  "Ġwould": 665,
-  "Ġwrit": 793,
-  "Ġy": 470,
-  "Ġyear": 607,
-  "Ġyears": 881,
-  "Ġâ": 454,
-  "ĠâĢ": 459,
-  "ĠâĢĵ": 522,
-  "ĠâĢĶ": 942,
-  "ĠĊ": 315,
-  "ġ": 222,
-  "Ģ": 223,
-  "ģ": 224,
-  "Ĥ": 225,
-  "ĥ": 226,
-  "Ħ": 227,
-  "ħ": 228,
-  "Ĩ": 229,
-  "ĩ": 230,
-  "Ī": 231,
-  "ī": 232,
-  "Ĭ": 233,
-  "ĭ": 234,
-  "Į": 235,
-  "į": 236,
-  "İ": 237,
-  "ı": 238,
-  "IJ": 239,
-  "ij": 240,
-  "Ĵ": 241,
-  "ĵ": 242,
-  "Ķ": 243,
-  "ķ": 244,
-  "ĸ": 245,
-  "Ĺ": 246,
-  "ĺ": 247,
-  "Ļ": 248,
-  "ļ": 249,
-  "Ľ": 250,
-  "ľ": 251,
-  "Ŀ": 252,
-  "ŀ": 253,
-  "Ł": 254,
-  "ł": 255,
-  "Ń": 256
-}