beshiribrahim commited on
Commit
5e9adf5
·
verified ·
1 Parent(s): 9022c8c

Upload 9 files

Browse files
model/added_tokens.json CHANGED
@@ -1,206 +1,206 @@
1
  {
2
- "<mask>": 75859,
3
- "ace_Arab": 75860,
4
- "ace_Latn": 75861,
5
- "acm_Arab": 75862,
6
- "acq_Arab": 75863,
7
- "aeb_Arab": 75864,
8
- "afr_Latn": 75865,
9
- "ajp_Arab": 75866,
10
- "aka_Latn": 75867,
11
- "als_Latn": 75868,
12
- "amh_Ethi": 75869,
13
- "apc_Arab": 75870,
14
- "arb_Arab": 75871,
15
- "ars_Arab": 75872,
16
- "ary_Arab": 75873,
17
- "arz_Arab": 75874,
18
- "asm_Beng": 75875,
19
- "ast_Latn": 75876,
20
- "awa_Deva": 75877,
21
- "ayr_Latn": 75878,
22
- "azb_Arab": 75879,
23
- "azj_Latn": 75880,
24
- "bak_Cyrl": 75881,
25
- "bam_Latn": 75882,
26
- "ban_Latn": 75883,
27
- "bel_Cyrl": 75884,
28
- "bem_Latn": 75885,
29
- "ben_Beng": 75886,
30
- "bho_Deva": 75887,
31
- "bjn_Arab": 75888,
32
- "bjn_Latn": 75889,
33
- "bod_Tibt": 75890,
34
- "bos_Latn": 75891,
35
- "bug_Latn": 75892,
36
- "bul_Cyrl": 75893,
37
- "cat_Latn": 75894,
38
- "ceb_Latn": 75895,
39
- "ces_Latn": 75896,
40
- "cjk_Latn": 75897,
41
- "ckb_Arab": 75898,
42
- "crh_Latn": 75899,
43
- "cym_Latn": 75900,
44
- "dan_Latn": 75901,
45
- "deu_Latn": 75902,
46
- "dik_Latn": 75903,
47
- "dyu_Latn": 75904,
48
- "dzo_Tibt": 75905,
49
- "ell_Grek": 75906,
50
- "eng_Latn": 75907,
51
- "epo_Latn": 75908,
52
- "est_Latn": 75909,
53
- "eus_Latn": 75910,
54
- "ewe_Latn": 75911,
55
- "fao_Latn": 75912,
56
- "fij_Latn": 75913,
57
- "fin_Latn": 75914,
58
- "fon_Latn": 75915,
59
- "fra_Latn": 75916,
60
- "fur_Latn": 75917,
61
- "fuv_Latn": 75918,
62
- "gaz_Latn": 75919,
63
- "gla_Latn": 75920,
64
- "gle_Latn": 75921,
65
- "glg_Latn": 75922,
66
- "grn_Latn": 75923,
67
- "guj_Gujr": 75924,
68
- "hat_Latn": 75925,
69
- "hau_Latn": 75926,
70
- "heb_Hebr": 75927,
71
- "hin_Deva": 75928,
72
- "hne_Deva": 75929,
73
- "hrv_Latn": 75930,
74
- "hun_Latn": 75931,
75
- "hye_Armn": 75932,
76
- "ibo_Latn": 75933,
77
- "ilo_Latn": 75934,
78
- "ind_Latn": 75935,
79
- "isl_Latn": 75936,
80
- "ita_Latn": 75937,
81
- "jav_Latn": 75938,
82
- "jpn_Jpan": 75939,
83
- "kab_Latn": 75940,
84
- "kac_Latn": 75941,
85
- "kam_Latn": 75942,
86
- "kan_Knda": 75943,
87
- "kas_Arab": 75944,
88
- "kas_Deva": 75945,
89
- "kat_Geor": 75946,
90
- "kaz_Cyrl": 75947,
91
- "kbp_Latn": 75948,
92
- "kea_Latn": 75949,
93
- "khk_Cyrl": 75950,
94
- "khm_Khmr": 75951,
95
- "kik_Latn": 75952,
96
- "kin_Latn": 75953,
97
- "kir_Cyrl": 75954,
98
- "kmb_Latn": 75955,
99
- "kmr_Latn": 75956,
100
- "knc_Arab": 75957,
101
- "knc_Latn": 75958,
102
- "kon_Latn": 75959,
103
- "kor_Hang": 75960,
104
- "lao_Laoo": 75961,
105
- "lij_Latn": 75962,
106
- "lim_Latn": 75963,
107
- "lin_Latn": 75964,
108
- "lit_Latn": 75965,
109
- "lmo_Latn": 75966,
110
- "ltg_Latn": 75967,
111
- "ltz_Latn": 75968,
112
- "lua_Latn": 75969,
113
- "lug_Latn": 75970,
114
- "luo_Latn": 75971,
115
- "lus_Latn": 75972,
116
- "lvs_Latn": 75973,
117
- "mag_Deva": 75974,
118
- "mai_Deva": 75975,
119
- "mal_Mlym": 75976,
120
- "mar_Deva": 75977,
121
- "min_Latn": 75978,
122
- "mkd_Cyrl": 75979,
123
- "mlt_Latn": 75980,
124
- "mni_Beng": 75981,
125
- "mos_Latn": 75982,
126
- "mri_Latn": 75983,
127
- "mya_Mymr": 75984,
128
- "nld_Latn": 75985,
129
- "nno_Latn": 75986,
130
- "nob_Latn": 75987,
131
- "npi_Deva": 75988,
132
- "nso_Latn": 75989,
133
- "nus_Latn": 75990,
134
- "nya_Latn": 75991,
135
- "oci_Latn": 75992,
136
- "ory_Orya": 75993,
137
- "pag_Latn": 75994,
138
- "pan_Guru": 75995,
139
- "pap_Latn": 75996,
140
- "pbt_Arab": 75997,
141
- "pes_Arab": 75998,
142
- "plt_Latn": 75999,
143
- "pol_Latn": 76000,
144
- "por_Latn": 76001,
145
- "prs_Arab": 76002,
146
- "quy_Latn": 76003,
147
- "ron_Latn": 76004,
148
- "run_Latn": 76005,
149
- "rus_Cyrl": 76006,
150
- "sag_Latn": 76007,
151
- "san_Deva": 76008,
152
- "sat_Beng": 76009,
153
- "scn_Latn": 76010,
154
- "shn_Mymr": 76011,
155
- "sin_Sinh": 76012,
156
- "slk_Latn": 76013,
157
- "slv_Latn": 76014,
158
- "smo_Latn": 76015,
159
- "sna_Latn": 76016,
160
- "snd_Arab": 76017,
161
- "som_Latn": 76018,
162
- "sot_Latn": 76019,
163
- "spa_Latn": 76020,
164
- "srd_Latn": 76021,
165
- "srp_Cyrl": 76022,
166
- "ssw_Latn": 76023,
167
- "sun_Latn": 76024,
168
- "swe_Latn": 76025,
169
- "swh_Latn": 76026,
170
- "szl_Latn": 76027,
171
- "tam_Taml": 76028,
172
- "taq_Latn": 76029,
173
- "taq_Tfng": 76030,
174
- "tat_Cyrl": 76031,
175
- "tel_Telu": 76032,
176
- "tgk_Cyrl": 76033,
177
- "tgl_Latn": 76034,
178
- "tha_Thai": 76035,
179
- "tig_Ethi": 76036,
180
- "tir_Ethi": 76037,
181
- "tpi_Latn": 76038,
182
- "tsn_Latn": 76039,
183
- "tso_Latn": 76040,
184
- "tuk_Latn": 76041,
185
- "tum_Latn": 76042,
186
- "tur_Latn": 76043,
187
- "twi_Latn": 76044,
188
- "tzm_Tfng": 76045,
189
- "uig_Arab": 76046,
190
- "ukr_Cyrl": 76047,
191
- "umb_Latn": 76048,
192
- "urd_Arab": 76049,
193
- "uzn_Latn": 76050,
194
- "vec_Latn": 76051,
195
- "vie_Latn": 76052,
196
- "war_Latn": 76053,
197
- "wol_Latn": 76054,
198
- "xho_Latn": 76055,
199
- "ydd_Hebr": 76056,
200
- "yor_Latn": 76057,
201
- "yue_Hant": 76058,
202
- "zho_Hans": 76059,
203
- "zho_Hant": 76060,
204
- "zsm_Latn": 76061,
205
- "zul_Latn": 76062
206
  }
 
1
  {
2
+ "<mask>": 75861,
3
+ "ace_Arab": 75862,
4
+ "ace_Latn": 75863,
5
+ "acm_Arab": 75864,
6
+ "acq_Arab": 75865,
7
+ "aeb_Arab": 75866,
8
+ "afr_Latn": 75867,
9
+ "ajp_Arab": 75868,
10
+ "aka_Latn": 75869,
11
+ "als_Latn": 75870,
12
+ "amh_Ethi": 75871,
13
+ "apc_Arab": 75872,
14
+ "arb_Arab": 75873,
15
+ "ars_Arab": 75874,
16
+ "ary_Arab": 75875,
17
+ "arz_Arab": 75876,
18
+ "asm_Beng": 75877,
19
+ "ast_Latn": 75878,
20
+ "awa_Deva": 75879,
21
+ "ayr_Latn": 75880,
22
+ "azb_Arab": 75881,
23
+ "azj_Latn": 75882,
24
+ "bak_Cyrl": 75883,
25
+ "bam_Latn": 75884,
26
+ "ban_Latn": 75885,
27
+ "bel_Cyrl": 75886,
28
+ "bem_Latn": 75887,
29
+ "ben_Beng": 75888,
30
+ "bho_Deva": 75889,
31
+ "bjn_Arab": 75890,
32
+ "bjn_Latn": 75891,
33
+ "bod_Tibt": 75892,
34
+ "bos_Latn": 75893,
35
+ "bug_Latn": 75894,
36
+ "bul_Cyrl": 75895,
37
+ "cat_Latn": 75896,
38
+ "ceb_Latn": 75897,
39
+ "ces_Latn": 75898,
40
+ "cjk_Latn": 75899,
41
+ "ckb_Arab": 75900,
42
+ "crh_Latn": 75901,
43
+ "cym_Latn": 75902,
44
+ "dan_Latn": 75903,
45
+ "deu_Latn": 75904,
46
+ "dik_Latn": 75905,
47
+ "dyu_Latn": 75906,
48
+ "dzo_Tibt": 75907,
49
+ "ell_Grek": 75908,
50
+ "eng_Latn": 75909,
51
+ "epo_Latn": 75910,
52
+ "est_Latn": 75911,
53
+ "eus_Latn": 75912,
54
+ "ewe_Latn": 75913,
55
+ "fao_Latn": 75914,
56
+ "fij_Latn": 75915,
57
+ "fin_Latn": 75916,
58
+ "fon_Latn": 75917,
59
+ "fra_Latn": 75918,
60
+ "fur_Latn": 75919,
61
+ "fuv_Latn": 75920,
62
+ "gaz_Latn": 75921,
63
+ "gla_Latn": 75922,
64
+ "gle_Latn": 75923,
65
+ "glg_Latn": 75924,
66
+ "grn_Latn": 75925,
67
+ "guj_Gujr": 75926,
68
+ "hat_Latn": 75927,
69
+ "hau_Latn": 75928,
70
+ "heb_Hebr": 75929,
71
+ "hin_Deva": 75930,
72
+ "hne_Deva": 75931,
73
+ "hrv_Latn": 75932,
74
+ "hun_Latn": 75933,
75
+ "hye_Armn": 75934,
76
+ "ibo_Latn": 75935,
77
+ "ilo_Latn": 75936,
78
+ "ind_Latn": 75937,
79
+ "isl_Latn": 75938,
80
+ "ita_Latn": 75939,
81
+ "jav_Latn": 75940,
82
+ "jpn_Jpan": 75941,
83
+ "kab_Latn": 75942,
84
+ "kac_Latn": 75943,
85
+ "kam_Latn": 75944,
86
+ "kan_Knda": 75945,
87
+ "kas_Arab": 75946,
88
+ "kas_Deva": 75947,
89
+ "kat_Geor": 75948,
90
+ "kaz_Cyrl": 75949,
91
+ "kbp_Latn": 75950,
92
+ "kea_Latn": 75951,
93
+ "khk_Cyrl": 75952,
94
+ "khm_Khmr": 75953,
95
+ "kik_Latn": 75954,
96
+ "kin_Latn": 75955,
97
+ "kir_Cyrl": 75956,
98
+ "kmb_Latn": 75957,
99
+ "kmr_Latn": 75958,
100
+ "knc_Arab": 75959,
101
+ "knc_Latn": 75960,
102
+ "kon_Latn": 75961,
103
+ "kor_Hang": 75962,
104
+ "lao_Laoo": 75963,
105
+ "lij_Latn": 75964,
106
+ "lim_Latn": 75965,
107
+ "lin_Latn": 75966,
108
+ "lit_Latn": 75967,
109
+ "lmo_Latn": 75968,
110
+ "ltg_Latn": 75969,
111
+ "ltz_Latn": 75970,
112
+ "lua_Latn": 75971,
113
+ "lug_Latn": 75972,
114
+ "luo_Latn": 75973,
115
+ "lus_Latn": 75974,
116
+ "lvs_Latn": 75975,
117
+ "mag_Deva": 75976,
118
+ "mai_Deva": 75977,
119
+ "mal_Mlym": 75978,
120
+ "mar_Deva": 75979,
121
+ "min_Latn": 75980,
122
+ "mkd_Cyrl": 75981,
123
+ "mlt_Latn": 75982,
124
+ "mni_Beng": 75983,
125
+ "mos_Latn": 75984,
126
+ "mri_Latn": 75985,
127
+ "mya_Mymr": 75986,
128
+ "nld_Latn": 75987,
129
+ "nno_Latn": 75988,
130
+ "nob_Latn": 75989,
131
+ "npi_Deva": 75990,
132
+ "nso_Latn": 75991,
133
+ "nus_Latn": 75992,
134
+ "nya_Latn": 75993,
135
+ "oci_Latn": 75994,
136
+ "ory_Orya": 75995,
137
+ "pag_Latn": 75996,
138
+ "pan_Guru": 75997,
139
+ "pap_Latn": 75998,
140
+ "pbt_Arab": 75999,
141
+ "pes_Arab": 76000,
142
+ "plt_Latn": 76001,
143
+ "pol_Latn": 76002,
144
+ "por_Latn": 76003,
145
+ "prs_Arab": 76004,
146
+ "quy_Latn": 76005,
147
+ "ron_Latn": 76006,
148
+ "run_Latn": 76007,
149
+ "rus_Cyrl": 76008,
150
+ "sag_Latn": 76009,
151
+ "san_Deva": 76010,
152
+ "sat_Beng": 76011,
153
+ "scn_Latn": 76012,
154
+ "shn_Mymr": 76013,
155
+ "sin_Sinh": 76014,
156
+ "slk_Latn": 76015,
157
+ "slv_Latn": 76016,
158
+ "smo_Latn": 76017,
159
+ "sna_Latn": 76018,
160
+ "snd_Arab": 76019,
161
+ "som_Latn": 76020,
162
+ "sot_Latn": 76021,
163
+ "spa_Latn": 76022,
164
+ "srd_Latn": 76023,
165
+ "srp_Cyrl": 76024,
166
+ "ssw_Latn": 76025,
167
+ "sun_Latn": 76026,
168
+ "swe_Latn": 76027,
169
+ "swh_Latn": 76028,
170
+ "szl_Latn": 76029,
171
+ "tam_Taml": 76030,
172
+ "taq_Latn": 76031,
173
+ "taq_Tfng": 76032,
174
+ "tat_Cyrl": 76033,
175
+ "tel_Telu": 76034,
176
+ "tgk_Cyrl": 76035,
177
+ "tgl_Latn": 76036,
178
+ "tha_Thai": 76037,
179
+ "tig_Ethi": 76038,
180
+ "tir_Ethi": 76039,
181
+ "tpi_Latn": 76040,
182
+ "tsn_Latn": 76041,
183
+ "tso_Latn": 76042,
184
+ "tuk_Latn": 76043,
185
+ "tum_Latn": 76044,
186
+ "tur_Latn": 76045,
187
+ "twi_Latn": 76046,
188
+ "tzm_Tfng": 76047,
189
+ "uig_Arab": 76048,
190
+ "ukr_Cyrl": 76049,
191
+ "umb_Latn": 76050,
192
+ "urd_Arab": 76051,
193
+ "uzn_Latn": 76052,
194
+ "vec_Latn": 76053,
195
+ "vie_Latn": 76054,
196
+ "war_Latn": 76055,
197
+ "wol_Latn": 76056,
198
+ "xho_Latn": 76057,
199
+ "ydd_Hebr": 76058,
200
+ "yor_Latn": 76059,
201
+ "yue_Hant": 76060,
202
+ "zho_Hans": 76061,
203
+ "zho_Hant": 76062,
204
+ "zsm_Latn": 76063,
205
+ "zul_Latn": 76064
206
  }
model/config.json CHANGED
@@ -27,7 +27,7 @@
27
  "num_hidden_layers": 24,
28
  "pad_token_id": 1,
29
  "scale_embedding": true,
30
- "transformers_version": "4.56.1",
31
  "use_cache": true,
32
- "vocab_size": 76063
33
  }
 
27
  "num_hidden_layers": 24,
28
  "pad_token_id": 1,
29
  "scale_embedding": true,
30
+ "transformers_version": "4.57.3",
31
  "use_cache": true,
32
+ "vocab_size": 76065
33
  }
model/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7cd221e97cc66526b6c85c5993006e2dd1a072e2d9fdbdc9057aba2cd14a78e
3
- size 2326539296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a20fa0e7e10f04a299af825758ff0294cad175d508823a336284864ff6fcdc
3
+ size 2326547488
model/sentencepiece.bpe.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a931688f7c193487f9f8a319234474ffdb16f1672b5df9e0b879cdcc5a612dc8
3
- size 1559454
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f4f6cb6f0ca3139f421378140f8ceb3c6c6520461034ff5d2fd990bd35f99a
3
+ size 1559040
model/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
model/tokenizer_config.json CHANGED
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "75859": {
36
  "content": "<mask>",
37
  "lstrip": true,
38
  "normalized": true,
@@ -40,7 +40,7 @@
40
  "single_word": false,
41
  "special": true
42
  },
43
- "75860": {
44
  "content": "ace_Arab",
45
  "lstrip": false,
46
  "normalized": false,
@@ -48,7 +48,7 @@
48
  "single_word": false,
49
  "special": true
50
  },
51
- "75861": {
52
  "content": "ace_Latn",
53
  "lstrip": false,
54
  "normalized": false,
@@ -56,7 +56,7 @@
56
  "single_word": false,
57
  "special": true
58
  },
59
- "75862": {
60
  "content": "acm_Arab",
61
  "lstrip": false,
62
  "normalized": false,
@@ -64,7 +64,7 @@
64
  "single_word": false,
65
  "special": true
66
  },
67
- "75863": {
68
  "content": "acq_Arab",
69
  "lstrip": false,
70
  "normalized": false,
@@ -72,7 +72,7 @@
72
  "single_word": false,
73
  "special": true
74
  },
75
- "75864": {
76
  "content": "aeb_Arab",
77
  "lstrip": false,
78
  "normalized": false,
@@ -80,7 +80,7 @@
80
  "single_word": false,
81
  "special": true
82
  },
83
- "75865": {
84
  "content": "afr_Latn",
85
  "lstrip": false,
86
  "normalized": false,
@@ -88,7 +88,7 @@
88
  "single_word": false,
89
  "special": true
90
  },
91
- "75866": {
92
  "content": "ajp_Arab",
93
  "lstrip": false,
94
  "normalized": false,
@@ -96,7 +96,7 @@
96
  "single_word": false,
97
  "special": true
98
  },
99
- "75867": {
100
  "content": "aka_Latn",
101
  "lstrip": false,
102
  "normalized": false,
@@ -104,7 +104,7 @@
104
  "single_word": false,
105
  "special": true
106
  },
107
- "75868": {
108
  "content": "als_Latn",
109
  "lstrip": false,
110
  "normalized": false,
@@ -112,7 +112,7 @@
112
  "single_word": false,
113
  "special": true
114
  },
115
- "75869": {
116
  "content": "amh_Ethi",
117
  "lstrip": false,
118
  "normalized": false,
@@ -120,7 +120,7 @@
120
  "single_word": false,
121
  "special": true
122
  },
123
- "75870": {
124
  "content": "apc_Arab",
125
  "lstrip": false,
126
  "normalized": false,
@@ -128,7 +128,7 @@
128
  "single_word": false,
129
  "special": true
130
  },
131
- "75871": {
132
  "content": "arb_Arab",
133
  "lstrip": false,
134
  "normalized": false,
@@ -136,7 +136,7 @@
136
  "single_word": false,
137
  "special": true
138
  },
139
- "75872": {
140
  "content": "ars_Arab",
141
  "lstrip": false,
142
  "normalized": false,
@@ -144,7 +144,7 @@
144
  "single_word": false,
145
  "special": true
146
  },
147
- "75873": {
148
  "content": "ary_Arab",
149
  "lstrip": false,
150
  "normalized": false,
@@ -152,7 +152,7 @@
152
  "single_word": false,
153
  "special": true
154
  },
155
- "75874": {
156
  "content": "arz_Arab",
157
  "lstrip": false,
158
  "normalized": false,
@@ -160,7 +160,7 @@
160
  "single_word": false,
161
  "special": true
162
  },
163
- "75875": {
164
  "content": "asm_Beng",
165
  "lstrip": false,
166
  "normalized": false,
@@ -168,7 +168,7 @@
168
  "single_word": false,
169
  "special": true
170
  },
171
- "75876": {
172
  "content": "ast_Latn",
173
  "lstrip": false,
174
  "normalized": false,
@@ -176,7 +176,7 @@
176
  "single_word": false,
177
  "special": true
178
  },
179
- "75877": {
180
  "content": "awa_Deva",
181
  "lstrip": false,
182
  "normalized": false,
@@ -184,7 +184,7 @@
184
  "single_word": false,
185
  "special": true
186
  },
187
- "75878": {
188
  "content": "ayr_Latn",
189
  "lstrip": false,
190
  "normalized": false,
@@ -192,7 +192,7 @@
192
  "single_word": false,
193
  "special": true
194
  },
195
- "75879": {
196
  "content": "azb_Arab",
197
  "lstrip": false,
198
  "normalized": false,
@@ -200,7 +200,7 @@
200
  "single_word": false,
201
  "special": true
202
  },
203
- "75880": {
204
  "content": "azj_Latn",
205
  "lstrip": false,
206
  "normalized": false,
@@ -208,7 +208,7 @@
208
  "single_word": false,
209
  "special": true
210
  },
211
- "75881": {
212
  "content": "bak_Cyrl",
213
  "lstrip": false,
214
  "normalized": false,
@@ -216,7 +216,7 @@
216
  "single_word": false,
217
  "special": true
218
  },
219
- "75882": {
220
  "content": "bam_Latn",
221
  "lstrip": false,
222
  "normalized": false,
@@ -224,7 +224,7 @@
224
  "single_word": false,
225
  "special": true
226
  },
227
- "75883": {
228
  "content": "ban_Latn",
229
  "lstrip": false,
230
  "normalized": false,
@@ -232,7 +232,7 @@
232
  "single_word": false,
233
  "special": true
234
  },
235
- "75884": {
236
  "content": "bel_Cyrl",
237
  "lstrip": false,
238
  "normalized": false,
@@ -240,7 +240,7 @@
240
  "single_word": false,
241
  "special": true
242
  },
243
- "75885": {
244
  "content": "bem_Latn",
245
  "lstrip": false,
246
  "normalized": false,
@@ -248,7 +248,7 @@
248
  "single_word": false,
249
  "special": true
250
  },
251
- "75886": {
252
  "content": "ben_Beng",
253
  "lstrip": false,
254
  "normalized": false,
@@ -256,7 +256,7 @@
256
  "single_word": false,
257
  "special": true
258
  },
259
- "75887": {
260
  "content": "bho_Deva",
261
  "lstrip": false,
262
  "normalized": false,
@@ -264,7 +264,7 @@
264
  "single_word": false,
265
  "special": true
266
  },
267
- "75888": {
268
  "content": "bjn_Arab",
269
  "lstrip": false,
270
  "normalized": false,
@@ -272,7 +272,7 @@
272
  "single_word": false,
273
  "special": true
274
  },
275
- "75889": {
276
  "content": "bjn_Latn",
277
  "lstrip": false,
278
  "normalized": false,
@@ -280,7 +280,7 @@
280
  "single_word": false,
281
  "special": true
282
  },
283
- "75890": {
284
  "content": "bod_Tibt",
285
  "lstrip": false,
286
  "normalized": false,
@@ -288,7 +288,7 @@
288
  "single_word": false,
289
  "special": true
290
  },
291
- "75891": {
292
  "content": "bos_Latn",
293
  "lstrip": false,
294
  "normalized": false,
@@ -296,7 +296,7 @@
296
  "single_word": false,
297
  "special": true
298
  },
299
- "75892": {
300
  "content": "bug_Latn",
301
  "lstrip": false,
302
  "normalized": false,
@@ -304,7 +304,7 @@
304
  "single_word": false,
305
  "special": true
306
  },
307
- "75893": {
308
  "content": "bul_Cyrl",
309
  "lstrip": false,
310
  "normalized": false,
@@ -312,7 +312,7 @@
312
  "single_word": false,
313
  "special": true
314
  },
315
- "75894": {
316
  "content": "cat_Latn",
317
  "lstrip": false,
318
  "normalized": false,
@@ -320,7 +320,7 @@
320
  "single_word": false,
321
  "special": true
322
  },
323
- "75895": {
324
  "content": "ceb_Latn",
325
  "lstrip": false,
326
  "normalized": false,
@@ -328,7 +328,7 @@
328
  "single_word": false,
329
  "special": true
330
  },
331
- "75896": {
332
  "content": "ces_Latn",
333
  "lstrip": false,
334
  "normalized": false,
@@ -336,7 +336,7 @@
336
  "single_word": false,
337
  "special": true
338
  },
339
- "75897": {
340
  "content": "cjk_Latn",
341
  "lstrip": false,
342
  "normalized": false,
@@ -344,7 +344,7 @@
344
  "single_word": false,
345
  "special": true
346
  },
347
- "75898": {
348
  "content": "ckb_Arab",
349
  "lstrip": false,
350
  "normalized": false,
@@ -352,7 +352,7 @@
352
  "single_word": false,
353
  "special": true
354
  },
355
- "75899": {
356
  "content": "crh_Latn",
357
  "lstrip": false,
358
  "normalized": false,
@@ -360,7 +360,7 @@
360
  "single_word": false,
361
  "special": true
362
  },
363
- "75900": {
364
  "content": "cym_Latn",
365
  "lstrip": false,
366
  "normalized": false,
@@ -368,7 +368,7 @@
368
  "single_word": false,
369
  "special": true
370
  },
371
- "75901": {
372
  "content": "dan_Latn",
373
  "lstrip": false,
374
  "normalized": false,
@@ -376,7 +376,7 @@
376
  "single_word": false,
377
  "special": true
378
  },
379
- "75902": {
380
  "content": "deu_Latn",
381
  "lstrip": false,
382
  "normalized": false,
@@ -384,7 +384,7 @@
384
  "single_word": false,
385
  "special": true
386
  },
387
- "75903": {
388
  "content": "dik_Latn",
389
  "lstrip": false,
390
  "normalized": false,
@@ -392,7 +392,7 @@
392
  "single_word": false,
393
  "special": true
394
  },
395
- "75904": {
396
  "content": "dyu_Latn",
397
  "lstrip": false,
398
  "normalized": false,
@@ -400,7 +400,7 @@
400
  "single_word": false,
401
  "special": true
402
  },
403
- "75905": {
404
  "content": "dzo_Tibt",
405
  "lstrip": false,
406
  "normalized": false,
@@ -408,7 +408,7 @@
408
  "single_word": false,
409
  "special": true
410
  },
411
- "75906": {
412
  "content": "ell_Grek",
413
  "lstrip": false,
414
  "normalized": false,
@@ -416,7 +416,7 @@
416
  "single_word": false,
417
  "special": true
418
  },
419
- "75907": {
420
  "content": "eng_Latn",
421
  "lstrip": false,
422
  "normalized": false,
@@ -424,7 +424,7 @@
424
  "single_word": false,
425
  "special": true
426
  },
427
- "75908": {
428
  "content": "epo_Latn",
429
  "lstrip": false,
430
  "normalized": false,
@@ -432,7 +432,7 @@
432
  "single_word": false,
433
  "special": true
434
  },
435
- "75909": {
436
  "content": "est_Latn",
437
  "lstrip": false,
438
  "normalized": false,
@@ -440,7 +440,7 @@
440
  "single_word": false,
441
  "special": true
442
  },
443
- "75910": {
444
  "content": "eus_Latn",
445
  "lstrip": false,
446
  "normalized": false,
@@ -448,7 +448,7 @@
448
  "single_word": false,
449
  "special": true
450
  },
451
- "75911": {
452
  "content": "ewe_Latn",
453
  "lstrip": false,
454
  "normalized": false,
@@ -456,7 +456,7 @@
456
  "single_word": false,
457
  "special": true
458
  },
459
- "75912": {
460
  "content": "fao_Latn",
461
  "lstrip": false,
462
  "normalized": false,
@@ -464,7 +464,7 @@
464
  "single_word": false,
465
  "special": true
466
  },
467
- "75913": {
468
  "content": "fij_Latn",
469
  "lstrip": false,
470
  "normalized": false,
@@ -472,7 +472,7 @@
472
  "single_word": false,
473
  "special": true
474
  },
475
- "75914": {
476
  "content": "fin_Latn",
477
  "lstrip": false,
478
  "normalized": false,
@@ -480,7 +480,7 @@
480
  "single_word": false,
481
  "special": true
482
  },
483
- "75915": {
484
  "content": "fon_Latn",
485
  "lstrip": false,
486
  "normalized": false,
@@ -488,7 +488,7 @@
488
  "single_word": false,
489
  "special": true
490
  },
491
- "75916": {
492
  "content": "fra_Latn",
493
  "lstrip": false,
494
  "normalized": false,
@@ -496,7 +496,7 @@
496
  "single_word": false,
497
  "special": true
498
  },
499
- "75917": {
500
  "content": "fur_Latn",
501
  "lstrip": false,
502
  "normalized": false,
@@ -504,7 +504,7 @@
504
  "single_word": false,
505
  "special": true
506
  },
507
- "75918": {
508
  "content": "fuv_Latn",
509
  "lstrip": false,
510
  "normalized": false,
@@ -512,7 +512,7 @@
512
  "single_word": false,
513
  "special": true
514
  },
515
- "75919": {
516
  "content": "gaz_Latn",
517
  "lstrip": false,
518
  "normalized": false,
@@ -520,7 +520,7 @@
520
  "single_word": false,
521
  "special": true
522
  },
523
- "75920": {
524
  "content": "gla_Latn",
525
  "lstrip": false,
526
  "normalized": false,
@@ -528,7 +528,7 @@
528
  "single_word": false,
529
  "special": true
530
  },
531
- "75921": {
532
  "content": "gle_Latn",
533
  "lstrip": false,
534
  "normalized": false,
@@ -536,7 +536,7 @@
536
  "single_word": false,
537
  "special": true
538
  },
539
- "75922": {
540
  "content": "glg_Latn",
541
  "lstrip": false,
542
  "normalized": false,
@@ -544,7 +544,7 @@
544
  "single_word": false,
545
  "special": true
546
  },
547
- "75923": {
548
  "content": "grn_Latn",
549
  "lstrip": false,
550
  "normalized": false,
@@ -552,7 +552,7 @@
552
  "single_word": false,
553
  "special": true
554
  },
555
- "75924": {
556
  "content": "guj_Gujr",
557
  "lstrip": false,
558
  "normalized": false,
@@ -560,7 +560,7 @@
560
  "single_word": false,
561
  "special": true
562
  },
563
- "75925": {
564
  "content": "hat_Latn",
565
  "lstrip": false,
566
  "normalized": false,
@@ -568,7 +568,7 @@
568
  "single_word": false,
569
  "special": true
570
  },
571
- "75926": {
572
  "content": "hau_Latn",
573
  "lstrip": false,
574
  "normalized": false,
@@ -576,7 +576,7 @@
576
  "single_word": false,
577
  "special": true
578
  },
579
- "75927": {
580
  "content": "heb_Hebr",
581
  "lstrip": false,
582
  "normalized": false,
@@ -584,7 +584,7 @@
584
  "single_word": false,
585
  "special": true
586
  },
587
- "75928": {
588
  "content": "hin_Deva",
589
  "lstrip": false,
590
  "normalized": false,
@@ -592,7 +592,7 @@
592
  "single_word": false,
593
  "special": true
594
  },
595
- "75929": {
596
  "content": "hne_Deva",
597
  "lstrip": false,
598
  "normalized": false,
@@ -600,7 +600,7 @@
600
  "single_word": false,
601
  "special": true
602
  },
603
- "75930": {
604
  "content": "hrv_Latn",
605
  "lstrip": false,
606
  "normalized": false,
@@ -608,7 +608,7 @@
608
  "single_word": false,
609
  "special": true
610
  },
611
- "75931": {
612
  "content": "hun_Latn",
613
  "lstrip": false,
614
  "normalized": false,
@@ -616,7 +616,7 @@
616
  "single_word": false,
617
  "special": true
618
  },
619
- "75932": {
620
  "content": "hye_Armn",
621
  "lstrip": false,
622
  "normalized": false,
@@ -624,7 +624,7 @@
624
  "single_word": false,
625
  "special": true
626
  },
627
- "75933": {
628
  "content": "ibo_Latn",
629
  "lstrip": false,
630
  "normalized": false,
@@ -632,7 +632,7 @@
632
  "single_word": false,
633
  "special": true
634
  },
635
- "75934": {
636
  "content": "ilo_Latn",
637
  "lstrip": false,
638
  "normalized": false,
@@ -640,7 +640,7 @@
640
  "single_word": false,
641
  "special": true
642
  },
643
- "75935": {
644
  "content": "ind_Latn",
645
  "lstrip": false,
646
  "normalized": false,
@@ -648,7 +648,7 @@
648
  "single_word": false,
649
  "special": true
650
  },
651
- "75936": {
652
  "content": "isl_Latn",
653
  "lstrip": false,
654
  "normalized": false,
@@ -656,7 +656,7 @@
656
  "single_word": false,
657
  "special": true
658
  },
659
- "75937": {
660
  "content": "ita_Latn",
661
  "lstrip": false,
662
  "normalized": false,
@@ -664,7 +664,7 @@
664
  "single_word": false,
665
  "special": true
666
  },
667
- "75938": {
668
  "content": "jav_Latn",
669
  "lstrip": false,
670
  "normalized": false,
@@ -672,7 +672,7 @@
672
  "single_word": false,
673
  "special": true
674
  },
675
- "75939": {
676
  "content": "jpn_Jpan",
677
  "lstrip": false,
678
  "normalized": false,
@@ -680,7 +680,7 @@
680
  "single_word": false,
681
  "special": true
682
  },
683
- "75940": {
684
  "content": "kab_Latn",
685
  "lstrip": false,
686
  "normalized": false,
@@ -688,7 +688,7 @@
688
  "single_word": false,
689
  "special": true
690
  },
691
- "75941": {
692
  "content": "kac_Latn",
693
  "lstrip": false,
694
  "normalized": false,
@@ -696,7 +696,7 @@
696
  "single_word": false,
697
  "special": true
698
  },
699
- "75942": {
700
  "content": "kam_Latn",
701
  "lstrip": false,
702
  "normalized": false,
@@ -704,7 +704,7 @@
704
  "single_word": false,
705
  "special": true
706
  },
707
- "75943": {
708
  "content": "kan_Knda",
709
  "lstrip": false,
710
  "normalized": false,
@@ -712,7 +712,7 @@
712
  "single_word": false,
713
  "special": true
714
  },
715
- "75944": {
716
  "content": "kas_Arab",
717
  "lstrip": false,
718
  "normalized": false,
@@ -720,7 +720,7 @@
720
  "single_word": false,
721
  "special": true
722
  },
723
- "75945": {
724
  "content": "kas_Deva",
725
  "lstrip": false,
726
  "normalized": false,
@@ -728,7 +728,7 @@
728
  "single_word": false,
729
  "special": true
730
  },
731
- "75946": {
732
  "content": "kat_Geor",
733
  "lstrip": false,
734
  "normalized": false,
@@ -736,7 +736,7 @@
736
  "single_word": false,
737
  "special": true
738
  },
739
- "75947": {
740
  "content": "kaz_Cyrl",
741
  "lstrip": false,
742
  "normalized": false,
@@ -744,7 +744,7 @@
744
  "single_word": false,
745
  "special": true
746
  },
747
- "75948": {
748
  "content": "kbp_Latn",
749
  "lstrip": false,
750
  "normalized": false,
@@ -752,7 +752,7 @@
752
  "single_word": false,
753
  "special": true
754
  },
755
- "75949": {
756
  "content": "kea_Latn",
757
  "lstrip": false,
758
  "normalized": false,
@@ -760,7 +760,7 @@
760
  "single_word": false,
761
  "special": true
762
  },
763
- "75950": {
764
  "content": "khk_Cyrl",
765
  "lstrip": false,
766
  "normalized": false,
@@ -768,7 +768,7 @@
768
  "single_word": false,
769
  "special": true
770
  },
771
- "75951": {
772
  "content": "khm_Khmr",
773
  "lstrip": false,
774
  "normalized": false,
@@ -776,7 +776,7 @@
776
  "single_word": false,
777
  "special": true
778
  },
779
- "75952": {
780
  "content": "kik_Latn",
781
  "lstrip": false,
782
  "normalized": false,
@@ -784,7 +784,7 @@
784
  "single_word": false,
785
  "special": true
786
  },
787
- "75953": {
788
  "content": "kin_Latn",
789
  "lstrip": false,
790
  "normalized": false,
@@ -792,7 +792,7 @@
792
  "single_word": false,
793
  "special": true
794
  },
795
- "75954": {
796
  "content": "kir_Cyrl",
797
  "lstrip": false,
798
  "normalized": false,
@@ -800,7 +800,7 @@
800
  "single_word": false,
801
  "special": true
802
  },
803
- "75955": {
804
  "content": "kmb_Latn",
805
  "lstrip": false,
806
  "normalized": false,
@@ -808,7 +808,7 @@
808
  "single_word": false,
809
  "special": true
810
  },
811
- "75956": {
812
  "content": "kmr_Latn",
813
  "lstrip": false,
814
  "normalized": false,
@@ -816,7 +816,7 @@
816
  "single_word": false,
817
  "special": true
818
  },
819
- "75957": {
820
  "content": "knc_Arab",
821
  "lstrip": false,
822
  "normalized": false,
@@ -824,7 +824,7 @@
824
  "single_word": false,
825
  "special": true
826
  },
827
- "75958": {
828
  "content": "knc_Latn",
829
  "lstrip": false,
830
  "normalized": false,
@@ -832,7 +832,7 @@
832
  "single_word": false,
833
  "special": true
834
  },
835
- "75959": {
836
  "content": "kon_Latn",
837
  "lstrip": false,
838
  "normalized": false,
@@ -840,7 +840,7 @@
840
  "single_word": false,
841
  "special": true
842
  },
843
- "75960": {
844
  "content": "kor_Hang",
845
  "lstrip": false,
846
  "normalized": false,
@@ -848,7 +848,7 @@
848
  "single_word": false,
849
  "special": true
850
  },
851
- "75961": {
852
  "content": "lao_Laoo",
853
  "lstrip": false,
854
  "normalized": false,
@@ -856,7 +856,7 @@
856
  "single_word": false,
857
  "special": true
858
  },
859
- "75962": {
860
  "content": "lij_Latn",
861
  "lstrip": false,
862
  "normalized": false,
@@ -864,7 +864,7 @@
864
  "single_word": false,
865
  "special": true
866
  },
867
- "75963": {
868
  "content": "lim_Latn",
869
  "lstrip": false,
870
  "normalized": false,
@@ -872,7 +872,7 @@
872
  "single_word": false,
873
  "special": true
874
  },
875
- "75964": {
876
  "content": "lin_Latn",
877
  "lstrip": false,
878
  "normalized": false,
@@ -880,7 +880,7 @@
880
  "single_word": false,
881
  "special": true
882
  },
883
- "75965": {
884
  "content": "lit_Latn",
885
  "lstrip": false,
886
  "normalized": false,
@@ -888,7 +888,7 @@
888
  "single_word": false,
889
  "special": true
890
  },
891
- "75966": {
892
  "content": "lmo_Latn",
893
  "lstrip": false,
894
  "normalized": false,
@@ -896,7 +896,7 @@
896
  "single_word": false,
897
  "special": true
898
  },
899
- "75967": {
900
  "content": "ltg_Latn",
901
  "lstrip": false,
902
  "normalized": false,
@@ -904,7 +904,7 @@
904
  "single_word": false,
905
  "special": true
906
  },
907
- "75968": {
908
  "content": "ltz_Latn",
909
  "lstrip": false,
910
  "normalized": false,
@@ -912,7 +912,7 @@
912
  "single_word": false,
913
  "special": true
914
  },
915
- "75969": {
916
  "content": "lua_Latn",
917
  "lstrip": false,
918
  "normalized": false,
@@ -920,7 +920,7 @@
920
  "single_word": false,
921
  "special": true
922
  },
923
- "75970": {
924
  "content": "lug_Latn",
925
  "lstrip": false,
926
  "normalized": false,
@@ -928,7 +928,7 @@
928
  "single_word": false,
929
  "special": true
930
  },
931
- "75971": {
932
  "content": "luo_Latn",
933
  "lstrip": false,
934
  "normalized": false,
@@ -936,7 +936,7 @@
936
  "single_word": false,
937
  "special": true
938
  },
939
- "75972": {
940
  "content": "lus_Latn",
941
  "lstrip": false,
942
  "normalized": false,
@@ -944,7 +944,7 @@
944
  "single_word": false,
945
  "special": true
946
  },
947
- "75973": {
948
  "content": "lvs_Latn",
949
  "lstrip": false,
950
  "normalized": false,
@@ -952,7 +952,7 @@
952
  "single_word": false,
953
  "special": true
954
  },
955
- "75974": {
956
  "content": "mag_Deva",
957
  "lstrip": false,
958
  "normalized": false,
@@ -960,7 +960,7 @@
960
  "single_word": false,
961
  "special": true
962
  },
963
- "75975": {
964
  "content": "mai_Deva",
965
  "lstrip": false,
966
  "normalized": false,
@@ -968,7 +968,7 @@
968
  "single_word": false,
969
  "special": true
970
  },
971
- "75976": {
972
  "content": "mal_Mlym",
973
  "lstrip": false,
974
  "normalized": false,
@@ -976,7 +976,7 @@
976
  "single_word": false,
977
  "special": true
978
  },
979
- "75977": {
980
  "content": "mar_Deva",
981
  "lstrip": false,
982
  "normalized": false,
@@ -984,7 +984,7 @@
984
  "single_word": false,
985
  "special": true
986
  },
987
- "75978": {
988
  "content": "min_Latn",
989
  "lstrip": false,
990
  "normalized": false,
@@ -992,7 +992,7 @@
992
  "single_word": false,
993
  "special": true
994
  },
995
- "75979": {
996
  "content": "mkd_Cyrl",
997
  "lstrip": false,
998
  "normalized": false,
@@ -1000,7 +1000,7 @@
1000
  "single_word": false,
1001
  "special": true
1002
  },
1003
- "75980": {
1004
  "content": "mlt_Latn",
1005
  "lstrip": false,
1006
  "normalized": false,
@@ -1008,7 +1008,7 @@
1008
  "single_word": false,
1009
  "special": true
1010
  },
1011
- "75981": {
1012
  "content": "mni_Beng",
1013
  "lstrip": false,
1014
  "normalized": false,
@@ -1016,7 +1016,7 @@
1016
  "single_word": false,
1017
  "special": true
1018
  },
1019
- "75982": {
1020
  "content": "mos_Latn",
1021
  "lstrip": false,
1022
  "normalized": false,
@@ -1024,7 +1024,7 @@
1024
  "single_word": false,
1025
  "special": true
1026
  },
1027
- "75983": {
1028
  "content": "mri_Latn",
1029
  "lstrip": false,
1030
  "normalized": false,
@@ -1032,7 +1032,7 @@
1032
  "single_word": false,
1033
  "special": true
1034
  },
1035
- "75984": {
1036
  "content": "mya_Mymr",
1037
  "lstrip": false,
1038
  "normalized": false,
@@ -1040,7 +1040,7 @@
1040
  "single_word": false,
1041
  "special": true
1042
  },
1043
- "75985": {
1044
  "content": "nld_Latn",
1045
  "lstrip": false,
1046
  "normalized": false,
@@ -1048,7 +1048,7 @@
1048
  "single_word": false,
1049
  "special": true
1050
  },
1051
- "75986": {
1052
  "content": "nno_Latn",
1053
  "lstrip": false,
1054
  "normalized": false,
@@ -1056,7 +1056,7 @@
1056
  "single_word": false,
1057
  "special": true
1058
  },
1059
- "75987": {
1060
  "content": "nob_Latn",
1061
  "lstrip": false,
1062
  "normalized": false,
@@ -1064,7 +1064,7 @@
1064
  "single_word": false,
1065
  "special": true
1066
  },
1067
- "75988": {
1068
  "content": "npi_Deva",
1069
  "lstrip": false,
1070
  "normalized": false,
@@ -1072,7 +1072,7 @@
1072
  "single_word": false,
1073
  "special": true
1074
  },
1075
- "75989": {
1076
  "content": "nso_Latn",
1077
  "lstrip": false,
1078
  "normalized": false,
@@ -1080,7 +1080,7 @@
1080
  "single_word": false,
1081
  "special": true
1082
  },
1083
- "75990": {
1084
  "content": "nus_Latn",
1085
  "lstrip": false,
1086
  "normalized": false,
@@ -1088,7 +1088,7 @@
1088
  "single_word": false,
1089
  "special": true
1090
  },
1091
- "75991": {
1092
  "content": "nya_Latn",
1093
  "lstrip": false,
1094
  "normalized": false,
@@ -1096,7 +1096,7 @@
1096
  "single_word": false,
1097
  "special": true
1098
  },
1099
- "75992": {
1100
  "content": "oci_Latn",
1101
  "lstrip": false,
1102
  "normalized": false,
@@ -1104,7 +1104,7 @@
1104
  "single_word": false,
1105
  "special": true
1106
  },
1107
- "75993": {
1108
  "content": "ory_Orya",
1109
  "lstrip": false,
1110
  "normalized": false,
@@ -1112,7 +1112,7 @@
1112
  "single_word": false,
1113
  "special": true
1114
  },
1115
- "75994": {
1116
  "content": "pag_Latn",
1117
  "lstrip": false,
1118
  "normalized": false,
@@ -1120,7 +1120,7 @@
1120
  "single_word": false,
1121
  "special": true
1122
  },
1123
- "75995": {
1124
  "content": "pan_Guru",
1125
  "lstrip": false,
1126
  "normalized": false,
@@ -1128,7 +1128,7 @@
1128
  "single_word": false,
1129
  "special": true
1130
  },
1131
- "75996": {
1132
  "content": "pap_Latn",
1133
  "lstrip": false,
1134
  "normalized": false,
@@ -1136,7 +1136,7 @@
1136
  "single_word": false,
1137
  "special": true
1138
  },
1139
- "75997": {
1140
  "content": "pbt_Arab",
1141
  "lstrip": false,
1142
  "normalized": false,
@@ -1144,7 +1144,7 @@
1144
  "single_word": false,
1145
  "special": true
1146
  },
1147
- "75998": {
1148
  "content": "pes_Arab",
1149
  "lstrip": false,
1150
  "normalized": false,
@@ -1152,7 +1152,7 @@
1152
  "single_word": false,
1153
  "special": true
1154
  },
1155
- "75999": {
1156
  "content": "plt_Latn",
1157
  "lstrip": false,
1158
  "normalized": false,
@@ -1160,7 +1160,7 @@
1160
  "single_word": false,
1161
  "special": true
1162
  },
1163
- "76000": {
1164
  "content": "pol_Latn",
1165
  "lstrip": false,
1166
  "normalized": false,
@@ -1168,7 +1168,7 @@
1168
  "single_word": false,
1169
  "special": true
1170
  },
1171
- "76001": {
1172
  "content": "por_Latn",
1173
  "lstrip": false,
1174
  "normalized": false,
@@ -1176,7 +1176,7 @@
1176
  "single_word": false,
1177
  "special": true
1178
  },
1179
- "76002": {
1180
  "content": "prs_Arab",
1181
  "lstrip": false,
1182
  "normalized": false,
@@ -1184,7 +1184,7 @@
1184
  "single_word": false,
1185
  "special": true
1186
  },
1187
- "76003": {
1188
  "content": "quy_Latn",
1189
  "lstrip": false,
1190
  "normalized": false,
@@ -1192,7 +1192,7 @@
1192
  "single_word": false,
1193
  "special": true
1194
  },
1195
- "76004": {
1196
  "content": "ron_Latn",
1197
  "lstrip": false,
1198
  "normalized": false,
@@ -1200,7 +1200,7 @@
1200
  "single_word": false,
1201
  "special": true
1202
  },
1203
- "76005": {
1204
  "content": "run_Latn",
1205
  "lstrip": false,
1206
  "normalized": false,
@@ -1208,7 +1208,7 @@
1208
  "single_word": false,
1209
  "special": true
1210
  },
1211
- "76006": {
1212
  "content": "rus_Cyrl",
1213
  "lstrip": false,
1214
  "normalized": false,
@@ -1216,7 +1216,7 @@
1216
  "single_word": false,
1217
  "special": true
1218
  },
1219
- "76007": {
1220
  "content": "sag_Latn",
1221
  "lstrip": false,
1222
  "normalized": false,
@@ -1224,7 +1224,7 @@
1224
  "single_word": false,
1225
  "special": true
1226
  },
1227
- "76008": {
1228
  "content": "san_Deva",
1229
  "lstrip": false,
1230
  "normalized": false,
@@ -1232,7 +1232,7 @@
1232
  "single_word": false,
1233
  "special": true
1234
  },
1235
- "76009": {
1236
  "content": "sat_Beng",
1237
  "lstrip": false,
1238
  "normalized": false,
@@ -1240,7 +1240,7 @@
1240
  "single_word": false,
1241
  "special": true
1242
  },
1243
- "76010": {
1244
  "content": "scn_Latn",
1245
  "lstrip": false,
1246
  "normalized": false,
@@ -1248,7 +1248,7 @@
1248
  "single_word": false,
1249
  "special": true
1250
  },
1251
- "76011": {
1252
  "content": "shn_Mymr",
1253
  "lstrip": false,
1254
  "normalized": false,
@@ -1256,7 +1256,7 @@
1256
  "single_word": false,
1257
  "special": true
1258
  },
1259
- "76012": {
1260
  "content": "sin_Sinh",
1261
  "lstrip": false,
1262
  "normalized": false,
@@ -1264,7 +1264,7 @@
1264
  "single_word": false,
1265
  "special": true
1266
  },
1267
- "76013": {
1268
  "content": "slk_Latn",
1269
  "lstrip": false,
1270
  "normalized": false,
@@ -1272,7 +1272,7 @@
1272
  "single_word": false,
1273
  "special": true
1274
  },
1275
- "76014": {
1276
  "content": "slv_Latn",
1277
  "lstrip": false,
1278
  "normalized": false,
@@ -1280,7 +1280,7 @@
1280
  "single_word": false,
1281
  "special": true
1282
  },
1283
- "76015": {
1284
  "content": "smo_Latn",
1285
  "lstrip": false,
1286
  "normalized": false,
@@ -1288,7 +1288,7 @@
1288
  "single_word": false,
1289
  "special": true
1290
  },
1291
- "76016": {
1292
  "content": "sna_Latn",
1293
  "lstrip": false,
1294
  "normalized": false,
@@ -1296,7 +1296,7 @@
1296
  "single_word": false,
1297
  "special": true
1298
  },
1299
- "76017": {
1300
  "content": "snd_Arab",
1301
  "lstrip": false,
1302
  "normalized": false,
@@ -1304,7 +1304,7 @@
1304
  "single_word": false,
1305
  "special": true
1306
  },
1307
- "76018": {
1308
  "content": "som_Latn",
1309
  "lstrip": false,
1310
  "normalized": false,
@@ -1312,7 +1312,7 @@
1312
  "single_word": false,
1313
  "special": true
1314
  },
1315
- "76019": {
1316
  "content": "sot_Latn",
1317
  "lstrip": false,
1318
  "normalized": false,
@@ -1320,7 +1320,7 @@
1320
  "single_word": false,
1321
  "special": true
1322
  },
1323
- "76020": {
1324
  "content": "spa_Latn",
1325
  "lstrip": false,
1326
  "normalized": false,
@@ -1328,7 +1328,7 @@
1328
  "single_word": false,
1329
  "special": true
1330
  },
1331
- "76021": {
1332
  "content": "srd_Latn",
1333
  "lstrip": false,
1334
  "normalized": false,
@@ -1336,7 +1336,7 @@
1336
  "single_word": false,
1337
  "special": true
1338
  },
1339
- "76022": {
1340
  "content": "srp_Cyrl",
1341
  "lstrip": false,
1342
  "normalized": false,
@@ -1344,7 +1344,7 @@
1344
  "single_word": false,
1345
  "special": true
1346
  },
1347
- "76023": {
1348
  "content": "ssw_Latn",
1349
  "lstrip": false,
1350
  "normalized": false,
@@ -1352,7 +1352,7 @@
1352
  "single_word": false,
1353
  "special": true
1354
  },
1355
- "76024": {
1356
  "content": "sun_Latn",
1357
  "lstrip": false,
1358
  "normalized": false,
@@ -1360,7 +1360,7 @@
1360
  "single_word": false,
1361
  "special": true
1362
  },
1363
- "76025": {
1364
  "content": "swe_Latn",
1365
  "lstrip": false,
1366
  "normalized": false,
@@ -1368,7 +1368,7 @@
1368
  "single_word": false,
1369
  "special": true
1370
  },
1371
- "76026": {
1372
  "content": "swh_Latn",
1373
  "lstrip": false,
1374
  "normalized": false,
@@ -1376,7 +1376,7 @@
1376
  "single_word": false,
1377
  "special": true
1378
  },
1379
- "76027": {
1380
  "content": "szl_Latn",
1381
  "lstrip": false,
1382
  "normalized": false,
@@ -1384,7 +1384,7 @@
1384
  "single_word": false,
1385
  "special": true
1386
  },
1387
- "76028": {
1388
  "content": "tam_Taml",
1389
  "lstrip": false,
1390
  "normalized": false,
@@ -1392,7 +1392,7 @@
1392
  "single_word": false,
1393
  "special": true
1394
  },
1395
- "76029": {
1396
  "content": "taq_Latn",
1397
  "lstrip": false,
1398
  "normalized": false,
@@ -1400,7 +1400,7 @@
1400
  "single_word": false,
1401
  "special": true
1402
  },
1403
- "76030": {
1404
  "content": "taq_Tfng",
1405
  "lstrip": false,
1406
  "normalized": false,
@@ -1408,7 +1408,7 @@
1408
  "single_word": false,
1409
  "special": true
1410
  },
1411
- "76031": {
1412
  "content": "tat_Cyrl",
1413
  "lstrip": false,
1414
  "normalized": false,
@@ -1416,7 +1416,7 @@
1416
  "single_word": false,
1417
  "special": true
1418
  },
1419
- "76032": {
1420
  "content": "tel_Telu",
1421
  "lstrip": false,
1422
  "normalized": false,
@@ -1424,7 +1424,7 @@
1424
  "single_word": false,
1425
  "special": true
1426
  },
1427
- "76033": {
1428
  "content": "tgk_Cyrl",
1429
  "lstrip": false,
1430
  "normalized": false,
@@ -1432,7 +1432,7 @@
1432
  "single_word": false,
1433
  "special": true
1434
  },
1435
- "76034": {
1436
  "content": "tgl_Latn",
1437
  "lstrip": false,
1438
  "normalized": false,
@@ -1440,7 +1440,7 @@
1440
  "single_word": false,
1441
  "special": true
1442
  },
1443
- "76035": {
1444
  "content": "tha_Thai",
1445
  "lstrip": false,
1446
  "normalized": false,
@@ -1448,7 +1448,7 @@
1448
  "single_word": false,
1449
  "special": true
1450
  },
1451
- "76036": {
1452
  "content": "tig_Ethi",
1453
  "lstrip": false,
1454
  "normalized": false,
@@ -1456,7 +1456,7 @@
1456
  "single_word": false,
1457
  "special": true
1458
  },
1459
- "76037": {
1460
  "content": "tir_Ethi",
1461
  "lstrip": false,
1462
  "normalized": false,
@@ -1464,7 +1464,7 @@
1464
  "single_word": false,
1465
  "special": true
1466
  },
1467
- "76038": {
1468
  "content": "tpi_Latn",
1469
  "lstrip": false,
1470
  "normalized": false,
@@ -1472,7 +1472,7 @@
1472
  "single_word": false,
1473
  "special": true
1474
  },
1475
- "76039": {
1476
  "content": "tsn_Latn",
1477
  "lstrip": false,
1478
  "normalized": false,
@@ -1480,7 +1480,7 @@
1480
  "single_word": false,
1481
  "special": true
1482
  },
1483
- "76040": {
1484
  "content": "tso_Latn",
1485
  "lstrip": false,
1486
  "normalized": false,
@@ -1488,7 +1488,7 @@
1488
  "single_word": false,
1489
  "special": true
1490
  },
1491
- "76041": {
1492
  "content": "tuk_Latn",
1493
  "lstrip": false,
1494
  "normalized": false,
@@ -1496,7 +1496,7 @@
1496
  "single_word": false,
1497
  "special": true
1498
  },
1499
- "76042": {
1500
  "content": "tum_Latn",
1501
  "lstrip": false,
1502
  "normalized": false,
@@ -1504,7 +1504,7 @@
1504
  "single_word": false,
1505
  "special": true
1506
  },
1507
- "76043": {
1508
  "content": "tur_Latn",
1509
  "lstrip": false,
1510
  "normalized": false,
@@ -1512,7 +1512,7 @@
1512
  "single_word": false,
1513
  "special": true
1514
  },
1515
- "76044": {
1516
  "content": "twi_Latn",
1517
  "lstrip": false,
1518
  "normalized": false,
@@ -1520,7 +1520,7 @@
1520
  "single_word": false,
1521
  "special": true
1522
  },
1523
- "76045": {
1524
  "content": "tzm_Tfng",
1525
  "lstrip": false,
1526
  "normalized": false,
@@ -1528,7 +1528,7 @@
1528
  "single_word": false,
1529
  "special": true
1530
  },
1531
- "76046": {
1532
  "content": "uig_Arab",
1533
  "lstrip": false,
1534
  "normalized": false,
@@ -1536,7 +1536,7 @@
1536
  "single_word": false,
1537
  "special": true
1538
  },
1539
- "76047": {
1540
  "content": "ukr_Cyrl",
1541
  "lstrip": false,
1542
  "normalized": false,
@@ -1544,7 +1544,7 @@
1544
  "single_word": false,
1545
  "special": true
1546
  },
1547
- "76048": {
1548
  "content": "umb_Latn",
1549
  "lstrip": false,
1550
  "normalized": false,
@@ -1552,7 +1552,7 @@
1552
  "single_word": false,
1553
  "special": true
1554
  },
1555
- "76049": {
1556
  "content": "urd_Arab",
1557
  "lstrip": false,
1558
  "normalized": false,
@@ -1560,7 +1560,7 @@
1560
  "single_word": false,
1561
  "special": true
1562
  },
1563
- "76050": {
1564
  "content": "uzn_Latn",
1565
  "lstrip": false,
1566
  "normalized": false,
@@ -1568,7 +1568,7 @@
1568
  "single_word": false,
1569
  "special": true
1570
  },
1571
- "76051": {
1572
  "content": "vec_Latn",
1573
  "lstrip": false,
1574
  "normalized": false,
@@ -1576,7 +1576,7 @@
1576
  "single_word": false,
1577
  "special": true
1578
  },
1579
- "76052": {
1580
  "content": "vie_Latn",
1581
  "lstrip": false,
1582
  "normalized": false,
@@ -1584,7 +1584,7 @@
1584
  "single_word": false,
1585
  "special": true
1586
  },
1587
- "76053": {
1588
  "content": "war_Latn",
1589
  "lstrip": false,
1590
  "normalized": false,
@@ -1592,7 +1592,7 @@
1592
  "single_word": false,
1593
  "special": true
1594
  },
1595
- "76054": {
1596
  "content": "wol_Latn",
1597
  "lstrip": false,
1598
  "normalized": false,
@@ -1600,7 +1600,7 @@
1600
  "single_word": false,
1601
  "special": true
1602
  },
1603
- "76055": {
1604
  "content": "xho_Latn",
1605
  "lstrip": false,
1606
  "normalized": false,
@@ -1608,7 +1608,7 @@
1608
  "single_word": false,
1609
  "special": true
1610
  },
1611
- "76056": {
1612
  "content": "ydd_Hebr",
1613
  "lstrip": false,
1614
  "normalized": false,
@@ -1616,7 +1616,7 @@
1616
  "single_word": false,
1617
  "special": true
1618
  },
1619
- "76057": {
1620
  "content": "yor_Latn",
1621
  "lstrip": false,
1622
  "normalized": false,
@@ -1624,7 +1624,7 @@
1624
  "single_word": false,
1625
  "special": true
1626
  },
1627
- "76058": {
1628
  "content": "yue_Hant",
1629
  "lstrip": false,
1630
  "normalized": false,
@@ -1632,7 +1632,7 @@
1632
  "single_word": false,
1633
  "special": true
1634
  },
1635
- "76059": {
1636
  "content": "zho_Hans",
1637
  "lstrip": false,
1638
  "normalized": false,
@@ -1640,7 +1640,7 @@
1640
  "single_word": false,
1641
  "special": true
1642
  },
1643
- "76060": {
1644
  "content": "zho_Hant",
1645
  "lstrip": false,
1646
  "normalized": false,
@@ -1648,7 +1648,7 @@
1648
  "single_word": false,
1649
  "special": true
1650
  },
1651
- "76061": {
1652
  "content": "zsm_Latn",
1653
  "lstrip": false,
1654
  "normalized": false,
@@ -1656,7 +1656,7 @@
1656
  "single_word": false,
1657
  "special": true
1658
  },
1659
- "76062": {
1660
  "content": "zul_Latn",
1661
  "lstrip": false,
1662
  "normalized": false,
@@ -1877,12 +1877,16 @@
1877
  "extra_special_tokens": {},
1878
  "legacy_behaviour": false,
1879
  "mask_token": "<mask>",
 
1880
  "model_max_length": 1024,
1881
  "pad_token": "<pad>",
1882
  "sep_token": "</s>",
1883
  "sp_model_kwargs": {},
1884
  "src_lang": "tig_Ethi",
1885
- "tgt_lang": null,
 
1886
  "tokenizer_class": "NllbTokenizer",
 
 
1887
  "unk_token": "<unk>"
1888
  }
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "75861": {
36
  "content": "<mask>",
37
  "lstrip": true,
38
  "normalized": true,
 
40
  "single_word": false,
41
  "special": true
42
  },
43
+ "75862": {
44
  "content": "ace_Arab",
45
  "lstrip": false,
46
  "normalized": false,
 
48
  "single_word": false,
49
  "special": true
50
  },
51
+ "75863": {
52
  "content": "ace_Latn",
53
  "lstrip": false,
54
  "normalized": false,
 
56
  "single_word": false,
57
  "special": true
58
  },
59
+ "75864": {
60
  "content": "acm_Arab",
61
  "lstrip": false,
62
  "normalized": false,
 
64
  "single_word": false,
65
  "special": true
66
  },
67
+ "75865": {
68
  "content": "acq_Arab",
69
  "lstrip": false,
70
  "normalized": false,
 
72
  "single_word": false,
73
  "special": true
74
  },
75
+ "75866": {
76
  "content": "aeb_Arab",
77
  "lstrip": false,
78
  "normalized": false,
 
80
  "single_word": false,
81
  "special": true
82
  },
83
+ "75867": {
84
  "content": "afr_Latn",
85
  "lstrip": false,
86
  "normalized": false,
 
88
  "single_word": false,
89
  "special": true
90
  },
91
+ "75868": {
92
  "content": "ajp_Arab",
93
  "lstrip": false,
94
  "normalized": false,
 
96
  "single_word": false,
97
  "special": true
98
  },
99
+ "75869": {
100
  "content": "aka_Latn",
101
  "lstrip": false,
102
  "normalized": false,
 
104
  "single_word": false,
105
  "special": true
106
  },
107
+ "75870": {
108
  "content": "als_Latn",
109
  "lstrip": false,
110
  "normalized": false,
 
112
  "single_word": false,
113
  "special": true
114
  },
115
+ "75871": {
116
  "content": "amh_Ethi",
117
  "lstrip": false,
118
  "normalized": false,
 
120
  "single_word": false,
121
  "special": true
122
  },
123
+ "75872": {
124
  "content": "apc_Arab",
125
  "lstrip": false,
126
  "normalized": false,
 
128
  "single_word": false,
129
  "special": true
130
  },
131
+ "75873": {
132
  "content": "arb_Arab",
133
  "lstrip": false,
134
  "normalized": false,
 
136
  "single_word": false,
137
  "special": true
138
  },
139
+ "75874": {
140
  "content": "ars_Arab",
141
  "lstrip": false,
142
  "normalized": false,
 
144
  "single_word": false,
145
  "special": true
146
  },
147
+ "75875": {
148
  "content": "ary_Arab",
149
  "lstrip": false,
150
  "normalized": false,
 
152
  "single_word": false,
153
  "special": true
154
  },
155
+ "75876": {
156
  "content": "arz_Arab",
157
  "lstrip": false,
158
  "normalized": false,
 
160
  "single_word": false,
161
  "special": true
162
  },
163
+ "75877": {
164
  "content": "asm_Beng",
165
  "lstrip": false,
166
  "normalized": false,
 
168
  "single_word": false,
169
  "special": true
170
  },
171
+ "75878": {
172
  "content": "ast_Latn",
173
  "lstrip": false,
174
  "normalized": false,
 
176
  "single_word": false,
177
  "special": true
178
  },
179
+ "75879": {
180
  "content": "awa_Deva",
181
  "lstrip": false,
182
  "normalized": false,
 
184
  "single_word": false,
185
  "special": true
186
  },
187
+ "75880": {
188
  "content": "ayr_Latn",
189
  "lstrip": false,
190
  "normalized": false,
 
192
  "single_word": false,
193
  "special": true
194
  },
195
+ "75881": {
196
  "content": "azb_Arab",
197
  "lstrip": false,
198
  "normalized": false,
 
200
  "single_word": false,
201
  "special": true
202
  },
203
+ "75882": {
204
  "content": "azj_Latn",
205
  "lstrip": false,
206
  "normalized": false,
 
208
  "single_word": false,
209
  "special": true
210
  },
211
+ "75883": {
212
  "content": "bak_Cyrl",
213
  "lstrip": false,
214
  "normalized": false,
 
216
  "single_word": false,
217
  "special": true
218
  },
219
+ "75884": {
220
  "content": "bam_Latn",
221
  "lstrip": false,
222
  "normalized": false,
 
224
  "single_word": false,
225
  "special": true
226
  },
227
+ "75885": {
228
  "content": "ban_Latn",
229
  "lstrip": false,
230
  "normalized": false,
 
232
  "single_word": false,
233
  "special": true
234
  },
235
+ "75886": {
236
  "content": "bel_Cyrl",
237
  "lstrip": false,
238
  "normalized": false,
 
240
  "single_word": false,
241
  "special": true
242
  },
243
+ "75887": {
244
  "content": "bem_Latn",
245
  "lstrip": false,
246
  "normalized": false,
 
248
  "single_word": false,
249
  "special": true
250
  },
251
+ "75888": {
252
  "content": "ben_Beng",
253
  "lstrip": false,
254
  "normalized": false,
 
256
  "single_word": false,
257
  "special": true
258
  },
259
+ "75889": {
260
  "content": "bho_Deva",
261
  "lstrip": false,
262
  "normalized": false,
 
264
  "single_word": false,
265
  "special": true
266
  },
267
+ "75890": {
268
  "content": "bjn_Arab",
269
  "lstrip": false,
270
  "normalized": false,
 
272
  "single_word": false,
273
  "special": true
274
  },
275
+ "75891": {
276
  "content": "bjn_Latn",
277
  "lstrip": false,
278
  "normalized": false,
 
280
  "single_word": false,
281
  "special": true
282
  },
283
+ "75892": {
284
  "content": "bod_Tibt",
285
  "lstrip": false,
286
  "normalized": false,
 
288
  "single_word": false,
289
  "special": true
290
  },
291
+ "75893": {
292
  "content": "bos_Latn",
293
  "lstrip": false,
294
  "normalized": false,
 
296
  "single_word": false,
297
  "special": true
298
  },
299
+ "75894": {
300
  "content": "bug_Latn",
301
  "lstrip": false,
302
  "normalized": false,
 
304
  "single_word": false,
305
  "special": true
306
  },
307
+ "75895": {
308
  "content": "bul_Cyrl",
309
  "lstrip": false,
310
  "normalized": false,
 
312
  "single_word": false,
313
  "special": true
314
  },
315
+ "75896": {
316
  "content": "cat_Latn",
317
  "lstrip": false,
318
  "normalized": false,
 
320
  "single_word": false,
321
  "special": true
322
  },
323
+ "75897": {
324
  "content": "ceb_Latn",
325
  "lstrip": false,
326
  "normalized": false,
 
328
  "single_word": false,
329
  "special": true
330
  },
331
+ "75898": {
332
  "content": "ces_Latn",
333
  "lstrip": false,
334
  "normalized": false,
 
336
  "single_word": false,
337
  "special": true
338
  },
339
+ "75899": {
340
  "content": "cjk_Latn",
341
  "lstrip": false,
342
  "normalized": false,
 
344
  "single_word": false,
345
  "special": true
346
  },
347
+ "75900": {
348
  "content": "ckb_Arab",
349
  "lstrip": false,
350
  "normalized": false,
 
352
  "single_word": false,
353
  "special": true
354
  },
355
+ "75901": {
356
  "content": "crh_Latn",
357
  "lstrip": false,
358
  "normalized": false,
 
360
  "single_word": false,
361
  "special": true
362
  },
363
+ "75902": {
364
  "content": "cym_Latn",
365
  "lstrip": false,
366
  "normalized": false,
 
368
  "single_word": false,
369
  "special": true
370
  },
371
+ "75903": {
372
  "content": "dan_Latn",
373
  "lstrip": false,
374
  "normalized": false,
 
376
  "single_word": false,
377
  "special": true
378
  },
379
+ "75904": {
380
  "content": "deu_Latn",
381
  "lstrip": false,
382
  "normalized": false,
 
384
  "single_word": false,
385
  "special": true
386
  },
387
+ "75905": {
388
  "content": "dik_Latn",
389
  "lstrip": false,
390
  "normalized": false,
 
392
  "single_word": false,
393
  "special": true
394
  },
395
+ "75906": {
396
  "content": "dyu_Latn",
397
  "lstrip": false,
398
  "normalized": false,
 
400
  "single_word": false,
401
  "special": true
402
  },
403
+ "75907": {
404
  "content": "dzo_Tibt",
405
  "lstrip": false,
406
  "normalized": false,
 
408
  "single_word": false,
409
  "special": true
410
  },
411
+ "75908": {
412
  "content": "ell_Grek",
413
  "lstrip": false,
414
  "normalized": false,
 
416
  "single_word": false,
417
  "special": true
418
  },
419
+ "75909": {
420
  "content": "eng_Latn",
421
  "lstrip": false,
422
  "normalized": false,
 
424
  "single_word": false,
425
  "special": true
426
  },
427
+ "75910": {
428
  "content": "epo_Latn",
429
  "lstrip": false,
430
  "normalized": false,
 
432
  "single_word": false,
433
  "special": true
434
  },
435
+ "75911": {
436
  "content": "est_Latn",
437
  "lstrip": false,
438
  "normalized": false,
 
440
  "single_word": false,
441
  "special": true
442
  },
443
+ "75912": {
444
  "content": "eus_Latn",
445
  "lstrip": false,
446
  "normalized": false,
 
448
  "single_word": false,
449
  "special": true
450
  },
451
+ "75913": {
452
  "content": "ewe_Latn",
453
  "lstrip": false,
454
  "normalized": false,
 
456
  "single_word": false,
457
  "special": true
458
  },
459
+ "75914": {
460
  "content": "fao_Latn",
461
  "lstrip": false,
462
  "normalized": false,
 
464
  "single_word": false,
465
  "special": true
466
  },
467
+ "75915": {
468
  "content": "fij_Latn",
469
  "lstrip": false,
470
  "normalized": false,
 
472
  "single_word": false,
473
  "special": true
474
  },
475
+ "75916": {
476
  "content": "fin_Latn",
477
  "lstrip": false,
478
  "normalized": false,
 
480
  "single_word": false,
481
  "special": true
482
  },
483
+ "75917": {
484
  "content": "fon_Latn",
485
  "lstrip": false,
486
  "normalized": false,
 
488
  "single_word": false,
489
  "special": true
490
  },
491
+ "75918": {
492
  "content": "fra_Latn",
493
  "lstrip": false,
494
  "normalized": false,
 
496
  "single_word": false,
497
  "special": true
498
  },
499
+ "75919": {
500
  "content": "fur_Latn",
501
  "lstrip": false,
502
  "normalized": false,
 
504
  "single_word": false,
505
  "special": true
506
  },
507
+ "75920": {
508
  "content": "fuv_Latn",
509
  "lstrip": false,
510
  "normalized": false,
 
512
  "single_word": false,
513
  "special": true
514
  },
515
+ "75921": {
516
  "content": "gaz_Latn",
517
  "lstrip": false,
518
  "normalized": false,
 
520
  "single_word": false,
521
  "special": true
522
  },
523
+ "75922": {
524
  "content": "gla_Latn",
525
  "lstrip": false,
526
  "normalized": false,
 
528
  "single_word": false,
529
  "special": true
530
  },
531
+ "75923": {
532
  "content": "gle_Latn",
533
  "lstrip": false,
534
  "normalized": false,
 
536
  "single_word": false,
537
  "special": true
538
  },
539
+ "75924": {
540
  "content": "glg_Latn",
541
  "lstrip": false,
542
  "normalized": false,
 
544
  "single_word": false,
545
  "special": true
546
  },
547
+ "75925": {
548
  "content": "grn_Latn",
549
  "lstrip": false,
550
  "normalized": false,
 
552
  "single_word": false,
553
  "special": true
554
  },
555
+ "75926": {
556
  "content": "guj_Gujr",
557
  "lstrip": false,
558
  "normalized": false,
 
560
  "single_word": false,
561
  "special": true
562
  },
563
+ "75927": {
564
  "content": "hat_Latn",
565
  "lstrip": false,
566
  "normalized": false,
 
568
  "single_word": false,
569
  "special": true
570
  },
571
+ "75928": {
572
  "content": "hau_Latn",
573
  "lstrip": false,
574
  "normalized": false,
 
576
  "single_word": false,
577
  "special": true
578
  },
579
+ "75929": {
580
  "content": "heb_Hebr",
581
  "lstrip": false,
582
  "normalized": false,
 
584
  "single_word": false,
585
  "special": true
586
  },
587
+ "75930": {
588
  "content": "hin_Deva",
589
  "lstrip": false,
590
  "normalized": false,
 
592
  "single_word": false,
593
  "special": true
594
  },
595
+ "75931": {
596
  "content": "hne_Deva",
597
  "lstrip": false,
598
  "normalized": false,
 
600
  "single_word": false,
601
  "special": true
602
  },
603
+ "75932": {
604
  "content": "hrv_Latn",
605
  "lstrip": false,
606
  "normalized": false,
 
608
  "single_word": false,
609
  "special": true
610
  },
611
+ "75933": {
612
  "content": "hun_Latn",
613
  "lstrip": false,
614
  "normalized": false,
 
616
  "single_word": false,
617
  "special": true
618
  },
619
+ "75934": {
620
  "content": "hye_Armn",
621
  "lstrip": false,
622
  "normalized": false,
 
624
  "single_word": false,
625
  "special": true
626
  },
627
+ "75935": {
628
  "content": "ibo_Latn",
629
  "lstrip": false,
630
  "normalized": false,
 
632
  "single_word": false,
633
  "special": true
634
  },
635
+ "75936": {
636
  "content": "ilo_Latn",
637
  "lstrip": false,
638
  "normalized": false,
 
640
  "single_word": false,
641
  "special": true
642
  },
643
+ "75937": {
644
  "content": "ind_Latn",
645
  "lstrip": false,
646
  "normalized": false,
 
648
  "single_word": false,
649
  "special": true
650
  },
651
+ "75938": {
652
  "content": "isl_Latn",
653
  "lstrip": false,
654
  "normalized": false,
 
656
  "single_word": false,
657
  "special": true
658
  },
659
+ "75939": {
660
  "content": "ita_Latn",
661
  "lstrip": false,
662
  "normalized": false,
 
664
  "single_word": false,
665
  "special": true
666
  },
667
+ "75940": {
668
  "content": "jav_Latn",
669
  "lstrip": false,
670
  "normalized": false,
 
672
  "single_word": false,
673
  "special": true
674
  },
675
+ "75941": {
676
  "content": "jpn_Jpan",
677
  "lstrip": false,
678
  "normalized": false,
 
680
  "single_word": false,
681
  "special": true
682
  },
683
+ "75942": {
684
  "content": "kab_Latn",
685
  "lstrip": false,
686
  "normalized": false,
 
688
  "single_word": false,
689
  "special": true
690
  },
691
+ "75943": {
692
  "content": "kac_Latn",
693
  "lstrip": false,
694
  "normalized": false,
 
696
  "single_word": false,
697
  "special": true
698
  },
699
+ "75944": {
700
  "content": "kam_Latn",
701
  "lstrip": false,
702
  "normalized": false,
 
704
  "single_word": false,
705
  "special": true
706
  },
707
+ "75945": {
708
  "content": "kan_Knda",
709
  "lstrip": false,
710
  "normalized": false,
 
712
  "single_word": false,
713
  "special": true
714
  },
715
+ "75946": {
716
  "content": "kas_Arab",
717
  "lstrip": false,
718
  "normalized": false,
 
720
  "single_word": false,
721
  "special": true
722
  },
723
+ "75947": {
724
  "content": "kas_Deva",
725
  "lstrip": false,
726
  "normalized": false,
 
728
  "single_word": false,
729
  "special": true
730
  },
731
+ "75948": {
732
  "content": "kat_Geor",
733
  "lstrip": false,
734
  "normalized": false,
 
736
  "single_word": false,
737
  "special": true
738
  },
739
+ "75949": {
740
  "content": "kaz_Cyrl",
741
  "lstrip": false,
742
  "normalized": false,
 
744
  "single_word": false,
745
  "special": true
746
  },
747
+ "75950": {
748
  "content": "kbp_Latn",
749
  "lstrip": false,
750
  "normalized": false,
 
752
  "single_word": false,
753
  "special": true
754
  },
755
+ "75951": {
756
  "content": "kea_Latn",
757
  "lstrip": false,
758
  "normalized": false,
 
760
  "single_word": false,
761
  "special": true
762
  },
763
+ "75952": {
764
  "content": "khk_Cyrl",
765
  "lstrip": false,
766
  "normalized": false,
 
768
  "single_word": false,
769
  "special": true
770
  },
771
+ "75953": {
772
  "content": "khm_Khmr",
773
  "lstrip": false,
774
  "normalized": false,
 
776
  "single_word": false,
777
  "special": true
778
  },
779
+ "75954": {
780
  "content": "kik_Latn",
781
  "lstrip": false,
782
  "normalized": false,
 
784
  "single_word": false,
785
  "special": true
786
  },
787
+ "75955": {
788
  "content": "kin_Latn",
789
  "lstrip": false,
790
  "normalized": false,
 
792
  "single_word": false,
793
  "special": true
794
  },
795
+ "75956": {
796
  "content": "kir_Cyrl",
797
  "lstrip": false,
798
  "normalized": false,
 
800
  "single_word": false,
801
  "special": true
802
  },
803
+ "75957": {
804
  "content": "kmb_Latn",
805
  "lstrip": false,
806
  "normalized": false,
 
808
  "single_word": false,
809
  "special": true
810
  },
811
+ "75958": {
812
  "content": "kmr_Latn",
813
  "lstrip": false,
814
  "normalized": false,
 
816
  "single_word": false,
817
  "special": true
818
  },
819
+ "75959": {
820
  "content": "knc_Arab",
821
  "lstrip": false,
822
  "normalized": false,
 
824
  "single_word": false,
825
  "special": true
826
  },
827
+ "75960": {
828
  "content": "knc_Latn",
829
  "lstrip": false,
830
  "normalized": false,
 
832
  "single_word": false,
833
  "special": true
834
  },
835
+ "75961": {
836
  "content": "kon_Latn",
837
  "lstrip": false,
838
  "normalized": false,
 
840
  "single_word": false,
841
  "special": true
842
  },
843
+ "75962": {
844
  "content": "kor_Hang",
845
  "lstrip": false,
846
  "normalized": false,
 
848
  "single_word": false,
849
  "special": true
850
  },
851
+ "75963": {
852
  "content": "lao_Laoo",
853
  "lstrip": false,
854
  "normalized": false,
 
856
  "single_word": false,
857
  "special": true
858
  },
859
+ "75964": {
860
  "content": "lij_Latn",
861
  "lstrip": false,
862
  "normalized": false,
 
864
  "single_word": false,
865
  "special": true
866
  },
867
+ "75965": {
868
  "content": "lim_Latn",
869
  "lstrip": false,
870
  "normalized": false,
 
872
  "single_word": false,
873
  "special": true
874
  },
875
+ "75966": {
876
  "content": "lin_Latn",
877
  "lstrip": false,
878
  "normalized": false,
 
880
  "single_word": false,
881
  "special": true
882
  },
883
+ "75967": {
884
  "content": "lit_Latn",
885
  "lstrip": false,
886
  "normalized": false,
 
888
  "single_word": false,
889
  "special": true
890
  },
891
+ "75968": {
892
  "content": "lmo_Latn",
893
  "lstrip": false,
894
  "normalized": false,
 
896
  "single_word": false,
897
  "special": true
898
  },
899
+ "75969": {
900
  "content": "ltg_Latn",
901
  "lstrip": false,
902
  "normalized": false,
 
904
  "single_word": false,
905
  "special": true
906
  },
907
+ "75970": {
908
  "content": "ltz_Latn",
909
  "lstrip": false,
910
  "normalized": false,
 
912
  "single_word": false,
913
  "special": true
914
  },
915
+ "75971": {
916
  "content": "lua_Latn",
917
  "lstrip": false,
918
  "normalized": false,
 
920
  "single_word": false,
921
  "special": true
922
  },
923
+ "75972": {
924
  "content": "lug_Latn",
925
  "lstrip": false,
926
  "normalized": false,
 
928
  "single_word": false,
929
  "special": true
930
  },
931
+ "75973": {
932
  "content": "luo_Latn",
933
  "lstrip": false,
934
  "normalized": false,
 
936
  "single_word": false,
937
  "special": true
938
  },
939
+ "75974": {
940
  "content": "lus_Latn",
941
  "lstrip": false,
942
  "normalized": false,
 
944
  "single_word": false,
945
  "special": true
946
  },
947
+ "75975": {
948
  "content": "lvs_Latn",
949
  "lstrip": false,
950
  "normalized": false,
 
952
  "single_word": false,
953
  "special": true
954
  },
955
+ "75976": {
956
  "content": "mag_Deva",
957
  "lstrip": false,
958
  "normalized": false,
 
960
  "single_word": false,
961
  "special": true
962
  },
963
+ "75977": {
964
  "content": "mai_Deva",
965
  "lstrip": false,
966
  "normalized": false,
 
968
  "single_word": false,
969
  "special": true
970
  },
971
+ "75978": {
972
  "content": "mal_Mlym",
973
  "lstrip": false,
974
  "normalized": false,
 
976
  "single_word": false,
977
  "special": true
978
  },
979
+ "75979": {
980
  "content": "mar_Deva",
981
  "lstrip": false,
982
  "normalized": false,
 
984
  "single_word": false,
985
  "special": true
986
  },
987
+ "75980": {
988
  "content": "min_Latn",
989
  "lstrip": false,
990
  "normalized": false,
 
992
  "single_word": false,
993
  "special": true
994
  },
995
+ "75981": {
996
  "content": "mkd_Cyrl",
997
  "lstrip": false,
998
  "normalized": false,
 
1000
  "single_word": false,
1001
  "special": true
1002
  },
1003
+ "75982": {
1004
  "content": "mlt_Latn",
1005
  "lstrip": false,
1006
  "normalized": false,
 
1008
  "single_word": false,
1009
  "special": true
1010
  },
1011
+ "75983": {
1012
  "content": "mni_Beng",
1013
  "lstrip": false,
1014
  "normalized": false,
 
1016
  "single_word": false,
1017
  "special": true
1018
  },
1019
+ "75984": {
1020
  "content": "mos_Latn",
1021
  "lstrip": false,
1022
  "normalized": false,
 
1024
  "single_word": false,
1025
  "special": true
1026
  },
1027
+ "75985": {
1028
  "content": "mri_Latn",
1029
  "lstrip": false,
1030
  "normalized": false,
 
1032
  "single_word": false,
1033
  "special": true
1034
  },
1035
+ "75986": {
1036
  "content": "mya_Mymr",
1037
  "lstrip": false,
1038
  "normalized": false,
 
1040
  "single_word": false,
1041
  "special": true
1042
  },
1043
+ "75987": {
1044
  "content": "nld_Latn",
1045
  "lstrip": false,
1046
  "normalized": false,
 
1048
  "single_word": false,
1049
  "special": true
1050
  },
1051
+ "75988": {
1052
  "content": "nno_Latn",
1053
  "lstrip": false,
1054
  "normalized": false,
 
1056
  "single_word": false,
1057
  "special": true
1058
  },
1059
+ "75989": {
1060
  "content": "nob_Latn",
1061
  "lstrip": false,
1062
  "normalized": false,
 
1064
  "single_word": false,
1065
  "special": true
1066
  },
1067
+ "75990": {
1068
  "content": "npi_Deva",
1069
  "lstrip": false,
1070
  "normalized": false,
 
1072
  "single_word": false,
1073
  "special": true
1074
  },
1075
+ "75991": {
1076
  "content": "nso_Latn",
1077
  "lstrip": false,
1078
  "normalized": false,
 
1080
  "single_word": false,
1081
  "special": true
1082
  },
1083
+ "75992": {
1084
  "content": "nus_Latn",
1085
  "lstrip": false,
1086
  "normalized": false,
 
1088
  "single_word": false,
1089
  "special": true
1090
  },
1091
+ "75993": {
1092
  "content": "nya_Latn",
1093
  "lstrip": false,
1094
  "normalized": false,
 
1096
  "single_word": false,
1097
  "special": true
1098
  },
1099
+ "75994": {
1100
  "content": "oci_Latn",
1101
  "lstrip": false,
1102
  "normalized": false,
 
1104
  "single_word": false,
1105
  "special": true
1106
  },
1107
+ "75995": {
1108
  "content": "ory_Orya",
1109
  "lstrip": false,
1110
  "normalized": false,
 
1112
  "single_word": false,
1113
  "special": true
1114
  },
1115
+ "75996": {
1116
  "content": "pag_Latn",
1117
  "lstrip": false,
1118
  "normalized": false,
 
1120
  "single_word": false,
1121
  "special": true
1122
  },
1123
+ "75997": {
1124
  "content": "pan_Guru",
1125
  "lstrip": false,
1126
  "normalized": false,
 
1128
  "single_word": false,
1129
  "special": true
1130
  },
1131
+ "75998": {
1132
  "content": "pap_Latn",
1133
  "lstrip": false,
1134
  "normalized": false,
 
1136
  "single_word": false,
1137
  "special": true
1138
  },
1139
+ "75999": {
1140
  "content": "pbt_Arab",
1141
  "lstrip": false,
1142
  "normalized": false,
 
1144
  "single_word": false,
1145
  "special": true
1146
  },
1147
+ "76000": {
1148
  "content": "pes_Arab",
1149
  "lstrip": false,
1150
  "normalized": false,
 
1152
  "single_word": false,
1153
  "special": true
1154
  },
1155
+ "76001": {
1156
  "content": "plt_Latn",
1157
  "lstrip": false,
1158
  "normalized": false,
 
1160
  "single_word": false,
1161
  "special": true
1162
  },
1163
+ "76002": {
1164
  "content": "pol_Latn",
1165
  "lstrip": false,
1166
  "normalized": false,
 
1168
  "single_word": false,
1169
  "special": true
1170
  },
1171
+ "76003": {
1172
  "content": "por_Latn",
1173
  "lstrip": false,
1174
  "normalized": false,
 
1176
  "single_word": false,
1177
  "special": true
1178
  },
1179
+ "76004": {
1180
  "content": "prs_Arab",
1181
  "lstrip": false,
1182
  "normalized": false,
 
1184
  "single_word": false,
1185
  "special": true
1186
  },
1187
+ "76005": {
1188
  "content": "quy_Latn",
1189
  "lstrip": false,
1190
  "normalized": false,
 
1192
  "single_word": false,
1193
  "special": true
1194
  },
1195
+ "76006": {
1196
  "content": "ron_Latn",
1197
  "lstrip": false,
1198
  "normalized": false,
 
1200
  "single_word": false,
1201
  "special": true
1202
  },
1203
+ "76007": {
1204
  "content": "run_Latn",
1205
  "lstrip": false,
1206
  "normalized": false,
 
1208
  "single_word": false,
1209
  "special": true
1210
  },
1211
+ "76008": {
1212
  "content": "rus_Cyrl",
1213
  "lstrip": false,
1214
  "normalized": false,
 
1216
  "single_word": false,
1217
  "special": true
1218
  },
1219
+ "76009": {
1220
  "content": "sag_Latn",
1221
  "lstrip": false,
1222
  "normalized": false,
 
1224
  "single_word": false,
1225
  "special": true
1226
  },
1227
+ "76010": {
1228
  "content": "san_Deva",
1229
  "lstrip": false,
1230
  "normalized": false,
 
1232
  "single_word": false,
1233
  "special": true
1234
  },
1235
+ "76011": {
1236
  "content": "sat_Beng",
1237
  "lstrip": false,
1238
  "normalized": false,
 
1240
  "single_word": false,
1241
  "special": true
1242
  },
1243
+ "76012": {
1244
  "content": "scn_Latn",
1245
  "lstrip": false,
1246
  "normalized": false,
 
1248
  "single_word": false,
1249
  "special": true
1250
  },
1251
+ "76013": {
1252
  "content": "shn_Mymr",
1253
  "lstrip": false,
1254
  "normalized": false,
 
1256
  "single_word": false,
1257
  "special": true
1258
  },
1259
+ "76014": {
1260
  "content": "sin_Sinh",
1261
  "lstrip": false,
1262
  "normalized": false,
 
1264
  "single_word": false,
1265
  "special": true
1266
  },
1267
+ "76015": {
1268
  "content": "slk_Latn",
1269
  "lstrip": false,
1270
  "normalized": false,
 
1272
  "single_word": false,
1273
  "special": true
1274
  },
1275
+ "76016": {
1276
  "content": "slv_Latn",
1277
  "lstrip": false,
1278
  "normalized": false,
 
1280
  "single_word": false,
1281
  "special": true
1282
  },
1283
+ "76017": {
1284
  "content": "smo_Latn",
1285
  "lstrip": false,
1286
  "normalized": false,
 
1288
  "single_word": false,
1289
  "special": true
1290
  },
1291
+ "76018": {
1292
  "content": "sna_Latn",
1293
  "lstrip": false,
1294
  "normalized": false,
 
1296
  "single_word": false,
1297
  "special": true
1298
  },
1299
+ "76019": {
1300
  "content": "snd_Arab",
1301
  "lstrip": false,
1302
  "normalized": false,
 
1304
  "single_word": false,
1305
  "special": true
1306
  },
1307
+ "76020": {
1308
  "content": "som_Latn",
1309
  "lstrip": false,
1310
  "normalized": false,
 
1312
  "single_word": false,
1313
  "special": true
1314
  },
1315
+ "76021": {
1316
  "content": "sot_Latn",
1317
  "lstrip": false,
1318
  "normalized": false,
 
1320
  "single_word": false,
1321
  "special": true
1322
  },
1323
+ "76022": {
1324
  "content": "spa_Latn",
1325
  "lstrip": false,
1326
  "normalized": false,
 
1328
  "single_word": false,
1329
  "special": true
1330
  },
1331
+ "76023": {
1332
  "content": "srd_Latn",
1333
  "lstrip": false,
1334
  "normalized": false,
 
1336
  "single_word": false,
1337
  "special": true
1338
  },
1339
+ "76024": {
1340
  "content": "srp_Cyrl",
1341
  "lstrip": false,
1342
  "normalized": false,
 
1344
  "single_word": false,
1345
  "special": true
1346
  },
1347
+ "76025": {
1348
  "content": "ssw_Latn",
1349
  "lstrip": false,
1350
  "normalized": false,
 
1352
  "single_word": false,
1353
  "special": true
1354
  },
1355
+ "76026": {
1356
  "content": "sun_Latn",
1357
  "lstrip": false,
1358
  "normalized": false,
 
1360
  "single_word": false,
1361
  "special": true
1362
  },
1363
+ "76027": {
1364
  "content": "swe_Latn",
1365
  "lstrip": false,
1366
  "normalized": false,
 
1368
  "single_word": false,
1369
  "special": true
1370
  },
1371
+ "76028": {
1372
  "content": "swh_Latn",
1373
  "lstrip": false,
1374
  "normalized": false,
 
1376
  "single_word": false,
1377
  "special": true
1378
  },
1379
+ "76029": {
1380
  "content": "szl_Latn",
1381
  "lstrip": false,
1382
  "normalized": false,
 
1384
  "single_word": false,
1385
  "special": true
1386
  },
1387
+ "76030": {
1388
  "content": "tam_Taml",
1389
  "lstrip": false,
1390
  "normalized": false,
 
1392
  "single_word": false,
1393
  "special": true
1394
  },
1395
+ "76031": {
1396
  "content": "taq_Latn",
1397
  "lstrip": false,
1398
  "normalized": false,
 
1400
  "single_word": false,
1401
  "special": true
1402
  },
1403
+ "76032": {
1404
  "content": "taq_Tfng",
1405
  "lstrip": false,
1406
  "normalized": false,
 
1408
  "single_word": false,
1409
  "special": true
1410
  },
1411
+ "76033": {
1412
  "content": "tat_Cyrl",
1413
  "lstrip": false,
1414
  "normalized": false,
 
1416
  "single_word": false,
1417
  "special": true
1418
  },
1419
+ "76034": {
1420
  "content": "tel_Telu",
1421
  "lstrip": false,
1422
  "normalized": false,
 
1424
  "single_word": false,
1425
  "special": true
1426
  },
1427
+ "76035": {
1428
  "content": "tgk_Cyrl",
1429
  "lstrip": false,
1430
  "normalized": false,
 
1432
  "single_word": false,
1433
  "special": true
1434
  },
1435
+ "76036": {
1436
  "content": "tgl_Latn",
1437
  "lstrip": false,
1438
  "normalized": false,
 
1440
  "single_word": false,
1441
  "special": true
1442
  },
1443
+ "76037": {
1444
  "content": "tha_Thai",
1445
  "lstrip": false,
1446
  "normalized": false,
 
1448
  "single_word": false,
1449
  "special": true
1450
  },
1451
+ "76038": {
1452
  "content": "tig_Ethi",
1453
  "lstrip": false,
1454
  "normalized": false,
 
1456
  "single_word": false,
1457
  "special": true
1458
  },
1459
+ "76039": {
1460
  "content": "tir_Ethi",
1461
  "lstrip": false,
1462
  "normalized": false,
 
1464
  "single_word": false,
1465
  "special": true
1466
  },
1467
+ "76040": {
1468
  "content": "tpi_Latn",
1469
  "lstrip": false,
1470
  "normalized": false,
 
1472
  "single_word": false,
1473
  "special": true
1474
  },
1475
+ "76041": {
1476
  "content": "tsn_Latn",
1477
  "lstrip": false,
1478
  "normalized": false,
 
1480
  "single_word": false,
1481
  "special": true
1482
  },
1483
+ "76042": {
1484
  "content": "tso_Latn",
1485
  "lstrip": false,
1486
  "normalized": false,
 
1488
  "single_word": false,
1489
  "special": true
1490
  },
1491
+ "76043": {
1492
  "content": "tuk_Latn",
1493
  "lstrip": false,
1494
  "normalized": false,
 
1496
  "single_word": false,
1497
  "special": true
1498
  },
1499
+ "76044": {
1500
  "content": "tum_Latn",
1501
  "lstrip": false,
1502
  "normalized": false,
 
1504
  "single_word": false,
1505
  "special": true
1506
  },
1507
+ "76045": {
1508
  "content": "tur_Latn",
1509
  "lstrip": false,
1510
  "normalized": false,
 
1512
  "single_word": false,
1513
  "special": true
1514
  },
1515
+ "76046": {
1516
  "content": "twi_Latn",
1517
  "lstrip": false,
1518
  "normalized": false,
 
1520
  "single_word": false,
1521
  "special": true
1522
  },
1523
+ "76047": {
1524
  "content": "tzm_Tfng",
1525
  "lstrip": false,
1526
  "normalized": false,
 
1528
  "single_word": false,
1529
  "special": true
1530
  },
1531
+ "76048": {
1532
  "content": "uig_Arab",
1533
  "lstrip": false,
1534
  "normalized": false,
 
1536
  "single_word": false,
1537
  "special": true
1538
  },
1539
+ "76049": {
1540
  "content": "ukr_Cyrl",
1541
  "lstrip": false,
1542
  "normalized": false,
 
1544
  "single_word": false,
1545
  "special": true
1546
  },
1547
+ "76050": {
1548
  "content": "umb_Latn",
1549
  "lstrip": false,
1550
  "normalized": false,
 
1552
  "single_word": false,
1553
  "special": true
1554
  },
1555
+ "76051": {
1556
  "content": "urd_Arab",
1557
  "lstrip": false,
1558
  "normalized": false,
 
1560
  "single_word": false,
1561
  "special": true
1562
  },
1563
+ "76052": {
1564
  "content": "uzn_Latn",
1565
  "lstrip": false,
1566
  "normalized": false,
 
1568
  "single_word": false,
1569
  "special": true
1570
  },
1571
+ "76053": {
1572
  "content": "vec_Latn",
1573
  "lstrip": false,
1574
  "normalized": false,
 
1576
  "single_word": false,
1577
  "special": true
1578
  },
1579
+ "76054": {
1580
  "content": "vie_Latn",
1581
  "lstrip": false,
1582
  "normalized": false,
 
1584
  "single_word": false,
1585
  "special": true
1586
  },
1587
+ "76055": {
1588
  "content": "war_Latn",
1589
  "lstrip": false,
1590
  "normalized": false,
 
1592
  "single_word": false,
1593
  "special": true
1594
  },
1595
+ "76056": {
1596
  "content": "wol_Latn",
1597
  "lstrip": false,
1598
  "normalized": false,
 
1600
  "single_word": false,
1601
  "special": true
1602
  },
1603
+ "76057": {
1604
  "content": "xho_Latn",
1605
  "lstrip": false,
1606
  "normalized": false,
 
1608
  "single_word": false,
1609
  "special": true
1610
  },
1611
+ "76058": {
1612
  "content": "ydd_Hebr",
1613
  "lstrip": false,
1614
  "normalized": false,
 
1616
  "single_word": false,
1617
  "special": true
1618
  },
1619
+ "76059": {
1620
  "content": "yor_Latn",
1621
  "lstrip": false,
1622
  "normalized": false,
 
1624
  "single_word": false,
1625
  "special": true
1626
  },
1627
+ "76060": {
1628
  "content": "yue_Hant",
1629
  "lstrip": false,
1630
  "normalized": false,
 
1632
  "single_word": false,
1633
  "special": true
1634
  },
1635
+ "76061": {
1636
  "content": "zho_Hans",
1637
  "lstrip": false,
1638
  "normalized": false,
 
1640
  "single_word": false,
1641
  "special": true
1642
  },
1643
+ "76062": {
1644
  "content": "zho_Hant",
1645
  "lstrip": false,
1646
  "normalized": false,
 
1648
  "single_word": false,
1649
  "special": true
1650
  },
1651
+ "76063": {
1652
  "content": "zsm_Latn",
1653
  "lstrip": false,
1654
  "normalized": false,
 
1656
  "single_word": false,
1657
  "special": true
1658
  },
1659
+ "76064": {
1660
  "content": "zul_Latn",
1661
  "lstrip": false,
1662
  "normalized": false,
 
1877
  "extra_special_tokens": {},
1878
  "legacy_behaviour": false,
1879
  "mask_token": "<mask>",
1880
+ "max_length": 128,
1881
  "model_max_length": 1024,
1882
  "pad_token": "<pad>",
1883
  "sep_token": "</s>",
1884
  "sp_model_kwargs": {},
1885
  "src_lang": "tig_Ethi",
1886
+ "stride": 0,
1887
+ "tgt_lang": "tig_Ethi",
1888
  "tokenizer_class": "NllbTokenizer",
1889
+ "truncation_side": "right",
1890
+ "truncation_strategy": "longest_first",
1891
  "unk_token": "<unk>"
1892
  }
model/training_history.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d8ffc94fc8e0e21021173338b2c3ee566ef29600cbc28e82ad503682a66f87
3
+ size 353699
model/validation_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "retrieval_accuracy": {
3
+ "eng_Latn": 77.0,
4
+ "arb_Arab": 91.5,
5
+ "swe_Latn": 82.0,
6
+ "tir_Ethi": 62.5,
7
+ "deu_Latn": 77.5,
8
+ "nno_Latn": 51.5,
9
+ "nob_Latn": 60.5
10
+ },
11
+ "average_accuracy": 71.78571428571429,
12
+ "final_loss": 1.0198285579681396,
13
+ "rating": "\u2b50\u2b50\u2b50\u2b50\u2b50 EXCELLENT",
14
+ "recommendation": "Ready for production use"
15
+ }