adapted_tokenizers/added-opt-fra/opt_500-add_full-fra-opt/added_tokens.json

{
  "\n\n\n": 50425,
  "\n\n\n\n": 50375,
  " \n": 50316,
  " Après": 50702,
  " Cette": 50525,
  " Dans": 50577,
  " Elle": 50337,
  " Ils": 50680,
  " Mais": 50741,
  " Une": 50629,
  " afin": 50663,
  " ainsi": 50352,
  " alors": 50358,
  " améric": 50484,
  " année": 50659,
  " années": 50403,
  " appel": 50583,
  " après": 50347,
  " aussi": 50349,
  " autre": 50623,
  " autres": 50458,
  " avait": 50457,
  " avant": 50418,
  " avec": 50271,
  " avoir": 50467,
  " ayant": 50692,
  " bien": 50450,
  " bâ": 50683,
  " bâti": 50752,
  " carac": 50632,
  " carrière": 50730,
  " celle": 50590,
  " celui": 50585,
  " ces": 50372,
  " cette": 50308,
  " chaque": 50738,
  " chez": 50670,
  " cin": 50445,
  " cinq": 50711,
  " classe": 50685,
  " comme": 50288,
  " commune": 50340,
  " communes": 50734,
  " compte": 50608,
  " conse": 50648,
  " consid": 50603,
  " constru": 50459,
  " contre": 50364,
  " cours": 50476,
  " cri": 50647,
  " cré": 50363,
  " cô": 50516,
  " dans": 50267,
  " depuis": 50400,
  " derni": 50385,
  " dernier": 50582,
  " deux": 50284,
  " deuxième": 50620,
  " deven": 50622,
  " devient": 50515,
  " différ": 50472,
  " doit": 50720,
  " donc": 50570,
  " durant": 50708,
  " déb": 50376,
  " début": 50471,
  " déc": 50295,
  " déf": 50462,
  " dém": 50482,
  " dép": 50434,
  " dépar": 50429,
  " département": 50505,
  " dés": 50684,
  " développ": 50481,
  " effet": 50740,
  " elle": 50305,
  " emp": 50543,
  " encore": 50490,
  " enf": 50594,
  " ense": 50751,
  " ensuite": 50613,
  " entre": 50296,
  " environ": 50706,
  " espè": 50587,
  " europé": 50689,
  " exemp": 50679,
  " fait": 50299,
  " famille": 50473,
  " fils": 50635,
  " fois": 50432,
  " fonction": 50549,
  " forme": 50584,
  " fran": 50317,
  " français": 50346,
  " française": 50596,
  " gouver": 50478,
  " gouvernement": 50586,
  " grande": 50545,
  " groupe": 50419,
  " guerre": 50534,
  " géné": 50355,
  " général": 50529,
  " hab": 50520,
  " ils": 50540,
  " indi": 50547,
  " internation": 50556,
  " jeu": 50673,
  " jou": 50359,
  " joue": 50599,
  " journ": 50759,
  " jours": 50756,
  " jus": 50354,
  " jusqu": 50409,
  " leur": 50326,
  " leurs": 50474,
  " ligne": 50564,
  " lors": 50328,
  " lui": 50324,
  " lég": 50546,
  " mais": 50292,
  " meille": 50662,
  " membre": 50742,
  " membres": 50700,
  " milli": 50640,
  " moins": 50513,
  " mois": 50609,
  " monde": 50451,
  " mondi": 50575,
  " mondiale": 50758,
  " moy": 50565,
  " muni": 50715,
  " méd": 50643,
  " médi": 50723,
  " mét": 50568,
  " même": 50339,
  " nationale": 50631,
  " niv": 50571,
  " niveau": 50638,
  " nombre": 50353,
  " nombreux": 50646,
  " nommé": 50749,
  " nord": 50494,
  " notamment": 50452,
  " nouv": 50319,
  " nouveau": 50503,
  " nouvelle": 50589,
  " né": 50367,
  " oc": 50598,
  " offici": 50633,
  " ou": 50278,
  " ouv": 50576,
  " où": 50338,
  " parc": 50750,
  " parti": 50275,
  " particu": 50579,
  " partie": 50361,
  " partir": 50499,
  " pendant": 50519,
  " permet": 50430,
  " personn": 50406,
  " personnes": 50710,
  " peti": 50650,
  " peu": 50433,
  " peut": 50389,
  " peuvent": 50727,
  " plusieurs": 50416,
  " poin": 50460,
  " poli": 50391,
  " politique": 50517,
  " porte": 50760,
  " pouv": 50528,
  " pouvoir": 50743,
  " premi": 50285,
  " première": 50368,
  " prend": 50707,
  " pris": 50762,
  " projet": 50567,
  " provin": 50728,
  " près": 50661,
  " pré": 50274,
  " préc": 50532,
  " présent": 50401,
  " présid": 50437,
  " président": 50554,
  " publi": 50350,
  " puis": 50332,
  " père": 50701,
  " péri": 50487,
  " période": 50639,
  " quat": 50442,
  " quatre": 50521,
  " quel": 50485,
  " quelques": 50604,
  " recher": 50716,
  " remp": 50404,
  " rencont": 50580,
  " représent": 50468,
  " reste": 50691,
  " retour": 50682,
  " retr": 50694,
  " reç": 50637,
  " ri": 50480,
  " roi": 50709,
  " réalis": 50477,
  " réc": 50693,
  " réf": 50618,
  " rég": 50315,
  " région": 50393,
  " rép": 50479,
  " rés": 50502,
  " rév": 50672,
  " rôle": 50748,
  " saison": 50483,
  " selon": 50559,
  " sera": 50688,
  " servi": 50475,
  " ses": 50289,
  " seul": 50746,
  " situé": 50657,
  " située": 50578,
  " siè": 50588,
  " soci": 50396,
  " société": 50636,
  " soit": 50498,
  " sont": 50273,
  " sorti": 50625,
  " sous": 50318,
  " souvent": 50736,
  " spéci": 50560,
  " sud": 50493,
  " suiv": 50411,
  " syst": 50656,
  " sé": 50440,
  " série": 50533,
  " tard": 50601,
  " temps": 50465,
  " territoire": 50724,
  " thé": 50593,
  " titre": 50507,
  " toujours": 50722,
  " tous": 50500,
  " tout": 50360,
  " toute": 50605,
  " trav": 50322,
  " trois": 50343,
  " trouve": 50614,
  " très": 50422,
  " télé": 50658,
  " utilis": 50441,
  " vie": 50512,
  " ville": 50387,
  " »,": 50548,
  " ».": 50501,
  " À": 50511,
  " États": 50522,
  " éc": 50334,
  " éch": 50671,
  " écrit": 50753,
  " ég": 50313,
  " également": 50331,
  " éle": 50518,
  " ép": 50456,
  " équi": 50761,
  " ét": 50279,
  " étaient": 50652,
  " était": 50341,
  " étant": 50703,
  " étu": 50466,
  " été": 50282,
  " év": 50402,
  " ê": 50362,
  " être": 50369,
  " œuv": 50705,
  "Au": 50655,
  "Biographie": 50510,
  "Dans": 50669,
  "Elle": 50678,
  "Histoire": 50642,
  "Unis": 50539,
  "aient": 50323,
  "aill": 50497,
  "aille": 50408,
  "aines": 50436,
  "aise": 50597,
  "aison": 50384,
  "aiss": 50562,
  "alement": 50294,
  "alif": 50739,
  "aliste": 50747,
  "alité": 50351,
  "amment": 50426,
  "anci": 50704,
  "anis": 50386,
  "année": 50651,
  "atique": 50644,
  "aume": 50690,
  "autres": 50514,
  "aî": 50380,
  "aît": 50610,
  "aï": 50572,
  "ché": 50504,
  "cid": 50524,
  "cident": 50755,
  "cien": 50390,
  "cip": 50302,
  "cipe": 50726,
  "cole": 50551,
  "cou": 50573,
  "cri": 50495,
  "cteur": 50602,
  "dic": 50731,
  "dition": 50553,
  "dre": 50624,
  "eau": 50301,
  "eaux": 50737,
  "ellement": 50461,
  "elles": 50330,
  "elon": 50395,
  "enant": 50581,
  "endre": 50449,
  "ennent": 50732,
  "entes": 50566,
  "enti": 50394,
  "entre": 50280,
  "erre": 50300,
  "fic": 50506,
  "fois": 50558,
  "ganis": 50455,
  "histoire": 50718,
  "hui": 50649,
  "hé": 50398,
  "ieurs": 50378,
  "ieux": 50469,
  "igine": 50668,
  "ilité": 50687,
  "insi": 50333,
  "iographie": 50491,
  "isme": 50626,
  "istes": 50489,
  "istoire": 50410,
  "istre": 50537,
  "ités": 50399,
  "iversité": 50544,
  "iè": 50298,
  "ième": 50374,
  "ière": 50681,
  "jourd": 50714,
  "jours": 50654,
  "lac": 50735,
  "lise": 50563,
  "lle": 50277,
  "lles": 50591,
  "lè": 50357,
  "mande": 50695,
  "mbl": 50665,
  "mbre": 50388,
  "mbres": 50664,
  "mé": 50379,
  "mée": 50464,
  "nement": 50342,
  "né": 50270,
  "née": 50336,
  "nées": 50321,
  "ographie": 50381,
  "oig": 50744,
  "oins": 50421,
  "oires": 50595,
  "oix": 50719,
  "ologie": 50486,
  "olu": 50424,
  "omme": 50439,
  "ommes": 50729,
  "onc": 50373,
  "onction": 50508,
  "onn": 50281,
  "opul": 50428,
  "origine": 50725,
  "orte": 50366,
  "orti": 50538,
  "ouest": 50677,
  "ouis": 50675,
  "ourd": 50600,
  "ourg": 50555,
  "ouv": 50268,
  "ouve": 50392,
  "ouvent": 50542,
  "pendant": 50619,
  "poque": 50617,
  "pris": 50550,
  "près": 50290,
  "puis": 50344,
  "qui": 50320,
  "quipe": 50427,
  "qué": 50607,
  "rale": 50569,
  "rande": 50448,
  "remi": 50283,
  "ribu": 50530,
  "rière": 50423,
  "rois": 50310,
  "roupe": 50377,
  "rée": 50492,
  "rés": 50536,
  "résent": 50438,
  "rê": 50526,
  "seau": 50676,
  "sig": 50674,
  "sion": 50303,
  "sionn": 50630,
  "sions": 50616,
  "sition": 50454,
  "sse": 50557,
  "suite": 50552,
  "tant": 50535,
  "tat": 50306,
  "tats": 50417,
  "tement": 50356,
  "tent": 50733,
  "teur": 50287,
  "teurs": 50435,
  "tient": 50541,
  "tifs": 50712,
  "tique": 50291,
  "tiques": 50382,
  "tit": 50443,
  "titu": 50365,
  "tiv": 50371,
  "tive": 50446,
  "tres": 50293,
  "ture": 50307,
  "té": 50266,
  "tég": 50561,
  "téri": 50612,
  "térieur": 50757,
  "téris": 50698,
  "tés": 50447,
  "ubli": 50311,
  "uerre": 50420,
  "uire": 50745,
  "uis": 50276,
  "urant": 50488,
  "urent": 50611,
  "urop": 50628,
  "urope": 50666,
  "uropé": 50653,
  "ussi": 50329,
  "utilis": 50397,
  "uvent": 50699,
  "velopp": 50470,
  "vient": 50415,
  "yant": 50621,
  "État": 50606,
  "âce": 50754,
  "âte": 50641,
  "âteau": 50717,
  "çais": 50335,
  "ède": 50627,
  "èg": 50697,
  "èle": 50721,
  "ème": 50414,
  "ène": 50453,
  "èrement": 50634,
  "èrent": 50696,
  "ères": 50345,
  "ès": 50269,
  "ètres": 50713,
  "éb": 50615,
  "éc": 50327,
  "éci": 50527,
  "éd": 50297,
  "édi": 50431,
  "ées": 50286,
  "ég": 50304,
  "él": 50574,
  "éli": 50667,
  "élé": 50463,
  "ém": 50325,
  "éné": 50312,
  "ép": 50383,
  "équipe": 50592,
  "éra": 50314,
  "ération": 50496,
  "éri": 50272,
  "éric": 50413,
  "érie": 50407,
  "éro": 50645,
  "éré": 50412,
  "éti": 50660,
  "été": 50348,
  "év": 50405,
  "ême": 50309,
  "ête": 50444,
  "être": 50531,
  "ôle": 50509,
  "ôt": 50686,
  "œ": 50370,
  "œuv": 50523,
  "’": 50265
}