Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,1061 @@
+{
+  "##_1": 106650,
+  "##_2": 106783,
+  "##ación": 106806,
+  "##ción": 106817,
+  "##án": 106617,
+  "##ée": 106794,
+  "##és": 106424,
+  "##ía": 106905,
+  "##ów": 106933,
+  "4liter": 106716,
+  "accelerate": 106281,
+  "accelerated": 106732,
+  "accelerating": 106454,
+  "accessibility": 106500,
+  "acción": 106092,
+  "accompagnement": 106256,
+  "accompagner": 106872,
+  "accountability": 105902,
+  "accountable": 106045,
+  "accroître": 106329,
+  "accès": 105914,
+  "acdi": 106193,
+  "acogida": 106834,
+  "acompañamiento": 106736,
+  "activités": 105921,
+  "actuación": 106792,
+  "adapt": 106345,
+  "adaptive": 106635,
+  "addendum": 106688,
+  "addresses": 106597,
+  "addressing": 105974,
+  "además": 106233,
+  "adequate": 106158,
+  "adjustment": 106502,
+  "admin": 105900,
+  "administratifs": 106470,
+  "administrations": 106680,
+  "adolescence": 106916,
+  "adolescents": 105975,
+  "advancing": 106168,
+  "adviser": 106497,
+  "advisors": 106271,
+  "advocacy": 105892,
+  "advocating": 106871,
+  "aecid": 106861,
+  "aefe": 106119,
+  "afdb": 105941,
+  "affecting": 106624,
+  "affectées": 106645,
+  "affordable": 106192,
+  "ageing": 106856,
+  "agendas": 106826,
+  "agri": 106287,
+  "agribusiness": 106443,
+  "agric": 106660,
+  "agriculteurs": 106637,
+  "agroforestry": 106882,
+  "agrícola": 106663,
+  "aiming": 106348,
+  "aligned": 106679,
+  "alimentación": 106421,
+  "alimentaire": 105912,
+  "alimentaires": 106661,
+  "alimentaria": 106018,
+  "alleviate": 106837,
+  "alleviation": 106320,
+  "alliances": 106266,
+  "allocation": 106100,
+  "alumnado": 106503,
+  "amelioration": 106928,
+  "amélioration": 105923,
+  "améliorer": 105924,
+  "aménagement": 106544,
+  "américa": 106727,
+  "analysed": 106476,
+  "analytical": 106459,
+  "analyze": 106613,
+  "andean": 106525,
+  "année": 106692,
+  "antimicrobial": 106699,
+  "análisis": 106501,
+  "apoyar": 106430,
+  "applying": 106892,
+  "apporté": 106815,
+  "appraisal": 106368,
+  "apprentissage": 106573,
+  "appropriation": 105969,
+  "approvisionnement": 106225,
+  "approximate": 106277,
+  "appuie": 106523,
+  "appuyer": 106124,
+  "aprendizaje": 106877,
+  "après": 106866,
+  "aquaculture": 106342,
+  "arid": 106705,
+  "asdb": 106353,
+  "asociaciones": 106585,
+  "asociación": 106302,
+  "assainissement": 105939,
+  "assess": 106034,
+  "assessed": 106272,
+  "assessing": 106504,
+  "assessments": 106157,
+  "assisting": 106428,
+  "associatifs": 106811,
+  "atención": 105987,
+  "audiovisual": 106314,
+  "audits": 106413,
+  "aulas": 106845,
+  "auprès": 106390,
+  "ausaid": 106567,
+  "autonomisation": 106671,
+  "autonomy": 106760,
+  "autorités": 106510,
+  "avian": 106796,
+  "ayudas": 106584,
+  "años": 106085,
+  "bamako": 106769,
+  "barriers": 106095,
+  "baseline": 106460,
+  "beans": 106775,
+  "becas": 106213,
+  "beneficiaries": 105993,
+  "beneficiarios": 106548,
+  "beneficiary": 106667,
+  "bijdrage": 106543,
+  "bilateral": 106056,
+  "biodiversité": 106614,
+  "biomass": 106700,
+  "biosphere": 106890,
+  "blend": 106498,
+  "bolivie": 106848,
+  "bourses": 105972,
+  "bridging": 106664,
+  "broader": 106405,
+  "budgeting": 106691,
+  "budgets": 106862,
+  "budgétaire": 106474,
+  "builds": 106354,
+  "básica": 106767,
+  "básicos": 106708,
+  "bénin": 106395,
+  "bénéficiaires": 106378,
+  "cacao": 106884,
+  "cadres": 106495,
+  "cambodge": 106891,
+  "campamentos": 106745,
+  "campaña": 106440,
+  "campesinas": 106436,
+  "capacidades": 105955,
+  "capacitación": 106052,
+  "capacities": 105885,
+  "capacité": 106070,
+  "capacités": 105909,
+  "caritas": 106310,
+  "carsi": 106590,
+  "catastrophes": 106673,
+  "cdcs": 106171,
+  "centred": 106317,
+  "cerp": 106473,
+  "cfli": 106071,
+  "channelcode": 106869,
+  "cholera": 106793,
+  "cida": 106086,
+  "ciudadana": 106636,
+  "ciudadanía": 106179,
+  "classrooms": 106194,
+  "clearance": 106243,
+  "climatique": 106491,
+  "climatiques": 106819,
+  "climático": 106840,
+  "clinics": 106579,
+  "cochabamba": 106841,
+  "cocoa": 106577,
+  "cohesion": 106279,
+  "colaboración": 106293,
+  "colectivos": 106582,
+  "collectivités": 106046,
+  "colombian": 106359,
+  "combating": 106227,
+  "comercialización": 106566,
+  "comité": 106580,
+  "comités": 106805,
+  "comm": 106678,
+  "commercialisation": 106759,
+  "commitments": 106212,
+  "commitmentsto": 106781,
+  "commodities": 106220,
+  "commodity": 105907,
+  "communautaire": 106099,
+  "communautaires": 106253,
+  "communauté": 106489,
+  "communautés": 106033,
+  "communicable": 106340,
+  "competence": 106477,
+  "competitiveness": 106000,
+  "complementary": 106432,
+  "compliance": 106152,
+  "complémentaire": 106571,
+  "composante": 106540,
+  "composantes": 106455,
+  "comprennent": 106389,
+  "compétences": 106113,
+  "comunicación": 106196,
+  "comunitaria": 106311,
+  "comunitarias": 106813,
+  "comunitario": 106437,
+  "comunitarios": 106908,
+  "conflits": 106169,
+  "connaissances": 106295,
+  "connectivity": 106410,
+  "conocimientos": 106545,
+  "consented": 106558,
+  "conservación": 106784,
+  "consolidación": 106864,
+  "consolidate": 106469,
+  "consolidating": 106920,
+  "consolidation": 105980,
+  "constituents": 106687,
+  "constraints": 106696,
+  "construcción": 105965,
+  "constructing": 106383,
+  "consultancy": 105977,
+  "consultants": 106355,
+  "consultation": 106230,
+  "consultations": 106328,
+  "contexts": 106482,
+  "continuation": 106032,
+  "continuidad": 106694,
+  "contractor": 106798,
+  "contractors": 106807,
+  "contractual": 106166,
+  "contribuer": 105999,
+  "contribuir": 105984,
+  "contributes": 105996,
+  "contrôle": 106322,
+  "convening": 106137,
+  "convenio": 106344,
+  "coop": 106172,
+  "cooperación": 105926,
+  "cooperatives": 106200,
+  "coopération": 105901,
+  "coordinación": 106519,
+  "coordinated": 106234,
+  "coordinating": 106608,
+  "corridors": 106868,
+  "counseling": 106917,
+  "counselling": 106569,
+  "covid": 105887,
+  "covid19": 106726,
+  "coûteuses": 106927,
+  "creación": 106129,
+  "crises": 106116,
+  "création": 106080,
+  "crédit": 106077,
+  "crédits": 106133,
+  "créer": 106739,
+  "csos": 106051,
+  "cultivation": 106407,
+  "cvca": 106336,
+  "côte": 106312,
+  "darfur": 106402,
+  "dcsd": 106622,
+  "ddhh": 106737,
+  "decent": 105983,
+  "decentralisation": 106396,
+  "decentralised": 106321,
+  "decentralization": 106162,
+  "decentralized": 106264,
+  "deepening": 106852,
+  "definitional": 106640,
+  "deforestation": 106450,
+  "delivering": 106269,
+  "demining": 106483,
+  "dept": 106075,
+  "designing": 106656,
+  "determinants": 106276,
+  "devis": 106303,
+  "devpt": 106803,
+  "devt": 106918,
+  "dfid": 106074,
+  "diagnostics": 106465,
+  "diakonia": 106711,
+  "diets": 106810,
+  "difusión": 106505,
+  "dignity": 106400,
+  "diplomacy": 106356,
+  "disabilities": 105947,
+  "disadvantaged": 106083,
+  "disasters": 106062,
+  "discapacidad": 106766,
+  "diseño": 106630,
+  "dispatch": 105938,
+  "displaced": 105929,
+  "displacement": 106221,
+  "disposal": 106222,
+  "disseminate": 106458,
+  "disseminating": 106748,
+  "dissemination": 106053,
+  "distress": 105979,
+  "distribución": 106728,
+  "diversification": 106185,
+  "docentes": 106833,
+  "donateurs": 106802,
+  "donneur": 106808,
+  "données": 106521,
+  "donor": 105971,
+  "donors": 106061,
+  "dotación": 106776,
+  "dotation": 106900,
+  "drafting": 106907,
+  "drought": 106019,
+  "durables": 106391,
+  "durée": 106772,
+  "duurzame": 106889,
+  "dvpt": 106480,
+  "décentralisation": 106561,
+  "déchets": 106747,
+  "défense": 106835,
+  "démocratique": 106296,
+  "département": 106780,
+  "dépenses": 106313,
+  "déplacées": 106404,
+  "développement": 105880,
+  "développer": 106346,
+  "ebola": 106235,
+  "ebrd": 106873,
+  "econ": 106593,
+  "economically": 106499,
+  "economies": 106331,
+  "economía": 106462,
+  "económica": 106308,
+  "económicas": 106902,
+  "económico": 106248,
+  "económicos": 106706,
+  "ecosystem": 106020,
+  "ecosystems": 106141,
+  "educ": 106238,
+  "educación": 105913,
+  "educate": 106649,
+  "educativa": 106208,
+  "educativas": 106595,
+  "educativo": 106257,
+  "educativos": 106349,
+  "educators": 106799,
+  "efficacité": 106386,
+  "efficiently": 106855,
+  "eidhr": 106326,
+  "ejecución": 106555,
+  "ejercicio": 106472,
+  "elaboración": 106527,
+  "elaboration": 106665,
+  "electrification": 106154,
+  "emergencies": 105991,
+  "emplois": 106538,
+  "employability": 106494,
+  "employers": 106123,
+  "empoderamiento": 106259,
+  "empower": 106089,
+  "empowered": 106632,
+  "empowering": 106014,
+  "empowerment": 105894,
+  "enables": 106375,
+  "enabling": 105931,
+  "encouraging": 106689,
+  "endowment": 105897,
+  "energies": 106730,
+  "engaging": 106251,
+  "enhance": 105891,
+  "enhancement": 106002,
+  "enhancing": 105898,
+  "enjeux": 106452,
+  "enpi": 106416,
+  "enseignants": 106333,
+  "ensuring": 106013,
+  "entrepreneurial": 106515,
+  "entrepreneurs": 106036,
+  "entrepreneurship": 105994,
+  "environmentally": 106240,
+  "environnementale": 106765,
+  "epidemic": 106224,
+  "equidad": 106258,
+  "equipamiento": 106316,
+  "equipping": 106309,
+  "equitable": 105976,
+  "eradication": 106252,
+  "escolares": 106859,
+  "españa": 106478,
+  "específico": 106744,
+  "essentiels": 106886,
+  "estrategias": 106367,
+  "está": 106244,
+  "están": 106703,
+  "eurasian": 106082,
+  "européenne": 106707,
+  "evaluación": 106554,
+  "evaluate": 106150,
+  "evaluating": 106911,
+  "evaluations": 106134,
+  "examine": 106715,
+  "exchanges": 106268,
+  "excluded": 106785,
+  "executing": 106824,
+  "expenditure": 105998,
+  "expenditures": 106684,
+  "expenses": 105978,
+  "exports": 106910,
+  "exposición": 106937,
+  "extractive": 106675,
+  "extremism": 106686,
+  "facilitating": 106126,
+  "facilitation": 106042,
+  "faciliter": 106850,
+  "familiale": 106618,
+  "faps": 106704,
+  "fasep": 106643,
+  "favoriser": 106406,
+  "fcil": 106003,
+  "feasibility": 105946,
+  "fellowships": 106626,
+  "fertilizer": 106816,
+  "filière": 106804,
+  "filières": 106587,
+  "financed": 106140,
+  "financement": 105944,
+  "financiers": 106646,
+  "financing": 105889,
+  "financière": 106319,
+  "financés": 106812,
+  "fishery": 106479,
+  "flandre": 106601,
+  "floods": 106181,
+  "flour": 106762,
+  "fomentar": 106516,
+  "fomento": 106508,
+  "formación": 105906,
+  "formulation": 106006,
+  "fortalecer": 106050,
+  "fortalecimiento": 105918,
+  "forums": 106723,
+  "fostering": 106173,
+  "fournir": 106186,
+  "fourniture": 106237,
+  "frameworks": 106147,
+  "francophonie": 106935,
+  "français": 105959,
+  "française": 106115,
+  "françaises": 106207,
+  "frontières": 106919,
+  "frontline": 106418,
+  "fspi": 106746,
+  "functioning": 106337,
+  "fundación": 106420,
+  "förderung": 106232,
+  "gaps": 106174,
+  "garantizar": 106361,
+  "gcrf": 106863,
+  "generación": 106627,
+  "generar": 106621,
+  "geothermal": 106753,
+  "gestión": 105951,
+  "globally": 106285,
+  "globaux": 106438,
+  "gouvernance": 105954,
+  "govt": 106915,
+  "grantee": 106035,
+  "grassroots": 106214,
+  "gratuities": 106537,
+  "greenhouse": 106592,
+  "groundwater": 106740,
+  "grâce": 106120,
+  "guarantee": 106209,
+  "guinée": 106408,
+  "género": 105945,
+  "général": 106197,
+  "générale": 106843,
+  "harmful": 106572,
+  "hazards": 106464,
+  "haïti": 106262,
+  "heating": 106563,
+  "herramientas": 106446,
+  "higiene": 106441,
+  "holistic": 106591,
+  "humanitaire": 105953,
+  "humanitaires": 106419,
+  "humanitaria": 106442,
+  "hydropower": 106315,
+  "hygiène": 106191,
+  "icrc": 106058,
+  "identifying": 106341,
+  "idps": 106047,
+  "idrc": 106122,
+  "ifrc": 106542,
+  "igualdad": 106325,
+  "ilea": 106801,
+  "illicit": 106894,
+  "immunization": 106467,
+  "implementación": 106164,
+  "implementing": 105922,
+  "improves": 106659,
+  "impulsar": 106906,
+  "impunity": 106773,
+  "imrs": 106327,
+  "incentives": 106729,
+  "incidence": 106456,
+  "incidencia": 106132,
+  "incl": 106365,
+  "inclusión": 106870,
+  "incomes": 106161,
+  "indemnities": 106556,
+  "indicators": 106199,
+  "indirect": 106429,
+  "indirectly": 106836,
+  "indígena": 106904,
+  "indígenas": 106110,
+  "inequalities": 106165,
+  "inequality": 106372,
+  "infantile": 106718,
+  "infectious": 106064,
+  "inform": 106015,
+  "información": 106211,
+  "informatiques": 106874,
+  "informative": 106758,
+  "infraestructuras": 106570,
+  "infrastructures": 106029,
+  "iniciativas": 106481,
+  "initiation": 106898,
+  "inondations": 106929,
+  "inputs": 106332,
+  "insecurity": 106215,
+  "insertion": 106324,
+  "instalación": 106893,
+  "institutionnel": 106135,
+  "insécurité": 106629,
+  "integración": 106616,
+  "integrate": 106290,
+  "integrating": 106364,
+  "intends": 106551,
+  "intercultural": 106267,
+  "internally": 106067,
+  "internship": 106250,
+  "internships": 106647,
+  "intervención": 106091,
+  "interventions": 105904,
+  "intégration": 106403,
+  "intégré": 106735,
+  "intégrée": 106564,
+  "intérieure": 106932,
+  "invest": 106216,
+  "investigación": 106160,
+  "investigative": 106384,
+  "investing": 106496,
+  "investissement": 106512,
+  "investissements": 106693,
+  "itsh": 106431,
+  "iwrm": 106619,
+  "jordanian": 106790,
+  "jordanie": 106934,
+  "jornadas": 106839,
+  "judiciary": 106602,
+  "juridique": 106774,
+  "jóvenes": 105968,
+  "kampala": 106888,
+  "kiribati": 106896,
+  "kits": 106301,
+  "kivu": 106254,
+  "koica": 106016,
+  "kyrgyz": 106488,
+  "kyrgyzstan": 106289,
+  "landscapes": 106654,
+  "latrines": 106423,
+  "lending": 106683,
+  "lesotho": 106334,
+  "leveraging": 106546,
+  "lgbti": 106842,
+  "libor": 106742,
+  "linkages": 106204,
+  "livelihood": 105943,
+  "livelihoods": 105899,
+  "liées": 106881,
+  "liés": 106734,
+  "logistical": 106524,
+  "logistique": 106568,
+  "lump": 106529,
+  "lycée": 106401,
+  "macro": 106670,
+  "macroeconomic": 106709,
+  "madres": 106858,
+  "mainstreaming": 106093,
+  "maize": 106825,
+  "malnutrition": 105981,
+  "managerial": 106463,
+  "manejo": 106533,
+  "manière": 106625,
+  "marché": 106210,
+  "marchés": 106676,
+  "marginalised": 106249,
+  "marginalized": 106038,
+  "maternelle": 106657,
+  "maternity": 106821,
+  "matière": 106004,
+  "matériel": 106658,
+  "mauritanie": 106818,
+  "mdgs": 106297,
+  "meaningful": 106922,
+  "mediation": 106283,
+  "medicines": 106107,
+  "mejora": 105936,
+  "mentoring": 106642,
+  "methodologies": 106653,
+  "methodology": 106373,
+  "mgmt": 105948,
+  "microfinance": 106027,
+  "migrant": 106145,
+  "migrants": 105925,
+  "migratory": 106895,
+  "ministries": 106242,
+  "ministère": 106048,
+  "minorities": 106363,
+  "misean": 106072,
+  "missionaries": 106562,
+  "mitigate": 106128,
+  "mitigating": 106763,
+  "mitigation": 105960,
+  "mobilisation": 106111,
+  "mobiliser": 106574,
+  "mobilité": 106851,
+  "mobilization": 106076,
+  "mobilizationand": 106921,
+  "mobilize": 106757,
+  "modelling": 106931,
+  "modernisation": 106241,
+  "modernization": 106049,
+  "monetization": 106560,
+  "montant": 106559,
+  "morbidity": 106357,
+  "msek": 106681,
+  "msmes": 106754,
+  "multilateral": 106078,
+  "multisector": 105940,
+  "multisectoral": 106417,
+  "mundus": 106682,
+  "mères": 106655,
+  "mécanismes": 106828,
+  "ménages": 106294,
+  "même": 106914,
+  "narcotics": 105882,
+  "neglected": 106800,
+  "negotiates": 106447,
+  "negotiation": 106187,
+  "neonatal": 106549,
+  "networking": 106024,
+  "newborn": 106040,
+  "ngos": 105896,
+  "niñas": 106011,
+  "niños": 105958,
+  "nonfat": 106814,
+  "norad": 106853,
+  "norms": 106379,
+  "nutricional": 106677,
+  "nutritional": 106121,
+  "nutritionnelle": 106583,
+  "ocha": 106229,
+  "oeuvre": 105963,
+  "ofda": 106284,
+  "offrent": 106849,
+  "offrir": 106603,
+  "ohchr": 106787,
+  "ondersteuning": 106912,
+  "ongd": 106936,
+  "opérations": 106323,
+  "organisational": 106273,
+  "organisationnelles": 106594,
+  "organización": 106189,
+  "organizational": 106023,
+  "orphans": 106387,
+  "osce": 106117,
+  "outputs": 106065,
+  "outreach": 106031,
+  "oversight": 106028,
+  "oxfam": 106190,
+  "p105": 106854,
+  "p185": 105915,
+  "p209": 105893,
+  "packages": 106475,
+  "pandemic": 106007,
+  "partenaires": 105952,
+  "partenariat": 106183,
+  "partenariats": 106741,
+  "participación": 105966,
+  "participative": 106722,
+  "participatory": 105986,
+  "particulièrement": 106557,
+  "partnerships": 105908,
+  "pauvres": 106439,
+  "pauvreté": 106054,
+  "país": 106195,
+  "países": 106073,
+  "peacebuilding": 106149,
+  "peacekeeping": 106846,
+  "peas": 106712,
+  "peasant": 106702,
+  "pepfar": 106125,
+  "permettra": 106755,
+  "perú": 106306,
+  "photovoltaic": 106923,
+  "pillar": 106860,
+  "pilotage": 106620,
+  "plaidoyer": 106752,
+  "planificación": 106838,
+  "planification": 106239,
+  "pnud": 106844,
+  "población": 105910,
+  "policymakers": 106539,
+  "polio": 106362,
+  "política": 106144,
+  "políticas": 106097,
+  "ponctuelles": 106879,
+  "poorest": 106246,
+  "possibilities": 106847,
+  "postgraduate": 106444,
+  "potable": 105916,
+  "poultry": 106751,
+  "practitioners": 106485,
+  "première": 106714,
+  "prep": 106832,
+  "preparatory": 106382,
+  "preparedness": 105934,
+  "prepositioning": 106335,
+  "prestation": 106633,
+  "prestations": 106791,
+  "prevalence": 106484,
+  "prevención": 106109,
+  "preventable": 106710,
+  "preventive": 106347,
+  "principled": 106925,
+  "priorities": 105985,
+  "privé": 106338,
+  "procurement": 105942,
+  "producción": 106022,
+  "productivas": 106733,
+  "productive": 105957,
+  "productivity": 105961,
+  "productivo": 106875,
+  "profesorado": 106638,
+  "prog": 105973,
+  "progr": 106260,
+  "programmatic": 106398,
+  "programmation": 106770,
+  "proj": 106094,
+  "promoción": 105997,
+  "promotes": 106175,
+  "promouvoir": 106131,
+  "promoviendo": 106820,
+  "prone": 106672,
+  "propuestas": 106651,
+  "prosperity": 106399,
+  "protección": 106084,
+  "protective": 106427,
+  "prácticas": 106178,
+  "préparation": 106461,
+  "prévention": 106057,
+  "prêt": 106575,
+  "psychosocial": 106143,
+  "purchases": 106509,
+  "pública": 106339,
+  "públicas": 106201,
+  "público": 106615,
+  "públicos": 106612,
+  "qualité": 105962,
+  "quotas": 106535,
+  "readiness": 106662,
+  "readjustment": 106553,
+  "realización": 106188,
+  "realization": 106720,
+  "receivables": 106924,
+  "reconciliation": 106059,
+  "recruitment": 106486,
+  "recycling": 106588,
+  "redacted": 106026,
+  "redd": 106330,
+  "reducción": 106611,
+  "referral": 106930,
+  "refinancement": 106867,
+  "reflexión": 106926,
+  "refuerzo": 106901,
+  "refugiada": 106883,
+  "refugiados": 106380,
+  "refund": 106768,
+  "región": 106081,
+  "rehab": 106282,
+  "rehabilitación": 106600,
+  "rehabilitate": 106786,
+  "rehabilitating": 106899,
+  "reinforce": 106487,
+  "reinforcement": 106278,
+  "reinforcing": 106609,
+  "reintegration": 106066,
+  "relevance": 106112,
+  "reliance": 106531,
+  "renewable": 105933,
+  "renewal": 106701,
+  "renforcement": 105888,
+  "renforcer": 105937,
+  "renforcées": 106669,
+  "reprod": 106138,
+  "reproductiva": 106913,
+  "reproductive": 105886,
+  "república": 106598,
+  "resettlement": 106628,
+  "resilience": 105890,
+  "resilient": 106001,
+  "responding": 106490,
+  "responsive": 106055,
+  "restoring": 106857,
+  "restructuring": 106300,
+  "returnees": 106247,
+  "robust": 106830,
+  "rssh": 106631,
+  "réalisation": 106136,
+  "récipiendaire": 106270,
+  "réduction": 106098,
+  "réduire": 106245,
+  "réforme": 106291,
+  "réfugiés": 106151,
+  "région": 105964,
+  "régional": 106205,
+  "régionale": 106586,
+  "régions": 106090,
+  "réhabilitation": 106087,
+  "répondre": 106492,
+  "réponse": 106226,
+  "république": 106104,
+  "réseau": 106043,
+  "réseaux": 106435,
+  "résilience": 106265,
+  "résultat": 106536,
+  "résultats": 106184,
+  "rôle": 106517,
+  "sadc": 106358,
+  "safeguarding": 106880,
+  "safer": 106779,
+  "saharan": 106041,
+  "saharaui": 106719,
+  "saharauis": 106756,
+  "sahel": 106105,
+  "saneamiento": 106142,
+  "sanit": 106771,
+  "sanitaire": 106299,
+  "sanitaires": 106304,
+  "sanitaria": 106360,
+  "sanitario": 106578,
+  "sanitary": 106218,
+  "sanitation": 105883,
+  "santé": 105884,
+  "scac": 105990,
+  "scaling": 106037,
+  "scholarships": 105905,
+  "scolaires": 106605,
+  "scolarisation": 106393,
+  "scoping": 106652,
+  "sdgs": 106176,
+  "secondment": 106146,
+  "secteurs": 106236,
+  "sectoral": 106060,
+  "securing": 106366,
+  "seekers": 106471,
+  "seguimiento": 106507,
+  "seminars": 106118,
+  "sensibilisation": 106068,
+  "sensibilización": 105982,
+  "sensibilizar": 106738,
+  "serv": 106274,
+  "será": 106887,
+  "serán": 106909,
+  "sewage": 106318,
+  "sewerage": 106170,
+  "sexes": 106511,
+  "sgbv": 106827,
+  "shocks": 106596,
+  "significatives": 106903,
+  "situación": 106012,
+  "skilled": 106721,
+  "slum": 106831,
+  "smallholder": 106044,
+  "smes": 106025,
+  "soberanía": 106589,
+  "socially": 106434,
+  "socioeconomic": 106623,
+  "société": 105956,
+  "soins": 105989,
+  "solidaria": 106641,
+  "solidaridad": 106307,
+  "solidarity": 106017,
+  "solidarité": 105970,
+  "somaliland": 106865,
+  "sostenibilidad": 106422,
+  "sostenible": 105992,
+  "sostenibles": 106797,
+  "soudan": 106513,
+  "soutenir": 106148,
+  "soya": 106724,
+  "specialists": 106506,
+  "spécifique": 106565,
+  "srhr": 106261,
+  "stabilisation": 106376,
+  "stabilization": 106411,
+  "stakeholder": 106203,
+  "stakeholders": 105928,
+  "stimulate": 106610,
+  "stratégie": 106182,
+  "stratégies": 106634,
+  "stratégique": 106449,
+  "strenghtening": 106409,
+  "strengthen": 105881,
+  "strengthened": 105903,
+  "strengthening": 105879,
+  "strengthens": 106466,
+  "stärkung": 106695,
+  "subdivisions": 106550,
+  "subprogram": 106876,
+  "subproject": 106778,
+  "subsector": 106789,
+  "subside": 106668,
+  "subsidies": 106280,
+  "subsidy": 106534,
+  "subsistance": 106451,
+  "subvention": 106008,
+  "subventions": 106493,
+  "sudanese": 106381,
+  "supp": 106674,
+  "supplementary": 106412,
+  "supportive": 106576,
+  "supérieur": 106155,
+  "surcharge": 106468,
+  "sustain": 106079,
+  "sustainability": 105917,
+  "sustainably": 106514,
+  "sustaining": 106457,
+  "swaziland": 106809,
+  "synergies": 106878,
+  "système": 105988,
+  "systèmes": 106101,
+  "sécurité": 105920,
+  "sénégal": 106153,
+  "tacis": 106448,
+  "tackling": 106644,
+  "tajikistan": 106114,
+  "también": 106180,
+  "tanzanie": 106788,
+  "targeting": 106206,
+  "taxation": 106292,
+  "taxing": 106552,
+  "tchad": 106231,
+  "tcpf": 106606,
+  "tempus": 106522,
+  "tertiary": 106795,
+  "thematic": 106103,
+  "tigray": 106731,
+  "timely": 106352,
+  "touchées": 106528,
+  "trainers": 106392,
+  "trainings": 106102,
+  "tranche": 106021,
+  "transboundary": 106666,
+  "transfers": 106690,
+  "transformación": 106581,
+  "transformative": 106782,
+  "transforming": 106648,
+  "transitional": 106275,
+  "transnational": 106750,
+  "transparency": 105930,
+  "través": 105911,
+  "tvet": 106433,
+  "twinning": 106369,
+  "técnica": 106106,
+  "técnicas": 106377,
+  "técnico": 106639,
+  "título": 105935,
+  "unaids": 106717,
+  "undergone": 106426,
+  "undertake": 106202,
+  "undp": 105932,
+  "unep": 106530,
+  "unfccc": 106822,
+  "unfpa": 106223,
+  "unhcr": 106009,
+  "unité": 106697,
+  "université": 106263,
+  "unrwa": 106394,
+  "unsafe": 106885,
+  "unspecified": 105919,
+  "unterstützung": 106604,
+  "upgrading": 106030,
+  "uptake": 106698,
+  "urgence": 105967,
+  "urgent": 106156,
+  "utilities": 106374,
+  "utilization": 106305,
+  "vaccination": 106518,
+  "vaccine": 106010,
+  "vaccines": 106139,
+  "valorisation": 106425,
+  "vegetable": 106063,
+  "veloppement": 106541,
+  "verification": 106088,
+  "viability": 106764,
+  "viable": 106228,
+  "vicitms": 105995,
+  "violations": 106130,
+  "violences": 106599,
+  "visibility": 106255,
+  "vocational": 105895,
+  "volet": 106286,
+  "volontaires": 106217,
+  "volontariat": 105950,
+  "vulnerabilidad": 106414,
+  "vulnerability": 106039,
+  "vulnerables": 106371,
+  "vulnérables": 106005,
+  "vérification": 106823,
+  "víctimas": 106526,
+  "wastewater": 106069,
+  "wellbeing": 106761,
+  "wetlands": 106749,
+  "womens": 106350,
+  "workforce": 106351,
+  "workplace": 106685,
+  "youths": 106777,
+  "áfrica": 106713,
+  "ámbito": 106198,
+  "área": 106397,
+  "áreas": 106532,
+  "échanges": 106288,
+  "échelle": 106607,
+  "école": 106298,
+  "écoles": 106096,
+  "écoliers": 106108,
+  "économie": 106385,
+  "économique": 105949,
+  "économiques": 106219,
+  "éducation": 105927,
+  "également": 106127,
+  "égalité": 106177,
+  "élaboration": 106445,
+  "élevage": 106743,
+  "élèves": 106897,
+  "énergie": 106547,
+  "équipement": 106829,
+  "équipements": 106725,
+  "établissement": 106415,
+  "établissements": 106520,
+  "état": 106163,
+  "étranger": 106370,
+  "étude": 106388,
+  "études": 106159,
+  "étudiants": 106453,
+  "évaluation": 106167,
+  "être": 106343
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "alex-miller/ODABert",
+  "architectures": [
+    "BertForMultiSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Significant disability objective",
+    "1": "Principal disability objective"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Principal disability objective": 1,
+    "Significant disability objective": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 106938
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b93438b54031654d8ab34c1019a1c163a9b60198446a1c1f1298fb9a25aea0a
+size 672720896

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aefc07b4363685c8bd08171c9b01feeca871c52b7305342556efe16f55e70f08
+size 4920