AnasAber commited on
Commit
04c4400
·
verified ·
1 Parent(s): 793ce21

Upload tokenizer

Browse files
sentencepiece.bpe.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:026a76827537db9f1348e4d5aaa127bb10a2f2ff633243f3a52d16be82d73f9d
3
- size 5165809
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
3
+ size 4852054
special_tokens_map.json CHANGED
@@ -1,103 +1,207 @@
1
  {
2
  "additional_special_tokens": [
3
- "__afr__",
4
- "__amh__",
5
- "__arb__",
6
- "__ary__",
7
- "__arz__",
8
- "__asm__",
9
- "__azj__",
10
- "__bel__",
11
- "__ben__",
12
- "__bos__",
13
- "__bul__",
14
- "__cat__",
15
- "__ceb__",
16
- "__ces__",
17
- "__ckb__",
18
- "__cmn__",
19
- "__cmn_Hant__",
20
- "__cym__",
21
- "__dan__",
22
- "__deu__",
23
- "__ell__",
24
- "__eng__",
25
- "__est__",
26
- "__eus__",
27
- "__fin__",
28
- "__fra__",
29
- "__fuv__",
30
- "__gaz__",
31
- "__gle__",
32
- "__glg__",
33
- "__guj__",
34
- "__heb__",
35
- "__hin__",
36
- "__hrv__",
37
- "__hun__",
38
- "__hye__",
39
- "__ibo__",
40
- "__ind__",
41
- "__isl__",
42
- "__ita__",
43
- "__jav__",
44
- "__jpn__",
45
- "__kan__",
46
- "__kat__",
47
- "__kaz__",
48
- "__khk__",
49
- "__khm__",
50
- "__kir__",
51
- "__kor__",
52
- "__lao__",
53
- "__lit__",
54
- "__lug__",
55
- "__luo__",
56
- "__lvs__",
57
- "__mai__",
58
- "__mal__",
59
- "__mar__",
60
- "__mkd__",
61
- "__mlt__",
62
- "__mni__",
63
- "__mya__",
64
- "__nld__",
65
- "__nno__",
66
- "__nob__",
67
- "__npi__",
68
- "__nya__",
69
- "__ory__",
70
- "__pan__",
71
- "__pbt__",
72
- "__pes__",
73
- "__pol__",
74
- "__por__",
75
- "__ron__",
76
- "__rus__",
77
- "__sat__",
78
- "__slk__",
79
- "__slv__",
80
- "__sna__",
81
- "__snd__",
82
- "__som__",
83
- "__spa__",
84
- "__srp__",
85
- "__swe__",
86
- "__swh__",
87
- "__tam__",
88
- "__tel__",
89
- "__tgk__",
90
- "__tgl__",
91
- "__tha__",
92
- "__tur__",
93
- "__ukr__",
94
- "__urd__",
95
- "__uzn__",
96
- "__vie__",
97
- "__yor__",
98
- "__yue__",
99
- "__zlm__",
100
- "__zul__"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
101
  ],
102
  "bos_token": {
103
  "content": "<s>",
@@ -120,6 +224,13 @@
120
  "rstrip": false,
121
  "single_word": false
122
  },
 
 
 
 
 
 
 
123
  "pad_token": {
124
  "content": "<pad>",
125
  "lstrip": false,
 
1
  {
2
  "additional_special_tokens": [
3
+ "ace_Arab",
4
+ "ace_Latn",
5
+ "acm_Arab",
6
+ "acq_Arab",
7
+ "aeb_Arab",
8
+ "afr_Latn",
9
+ "ajp_Arab",
10
+ "aka_Latn",
11
+ "amh_Ethi",
12
+ "apc_Arab",
13
+ "arb_Arab",
14
+ "ars_Arab",
15
+ "ary_Arab",
16
+ "arz_Arab",
17
+ "asm_Beng",
18
+ "ast_Latn",
19
+ "awa_Deva",
20
+ "ayr_Latn",
21
+ "azb_Arab",
22
+ "azj_Latn",
23
+ "bak_Cyrl",
24
+ "bam_Latn",
25
+ "ban_Latn",
26
+ "bel_Cyrl",
27
+ "bem_Latn",
28
+ "ben_Beng",
29
+ "bho_Deva",
30
+ "bjn_Arab",
31
+ "bjn_Latn",
32
+ "bod_Tibt",
33
+ "bos_Latn",
34
+ "bug_Latn",
35
+ "bul_Cyrl",
36
+ "cat_Latn",
37
+ "ceb_Latn",
38
+ "ces_Latn",
39
+ "cjk_Latn",
40
+ "ckb_Arab",
41
+ "crh_Latn",
42
+ "cym_Latn",
43
+ "dan_Latn",
44
+ "deu_Latn",
45
+ "dik_Latn",
46
+ "dyu_Latn",
47
+ "dzo_Tibt",
48
+ "ell_Grek",
49
+ "eng_Latn",
50
+ "epo_Latn",
51
+ "est_Latn",
52
+ "eus_Latn",
53
+ "ewe_Latn",
54
+ "fao_Latn",
55
+ "pes_Arab",
56
+ "fij_Latn",
57
+ "fin_Latn",
58
+ "fon_Latn",
59
+ "fra_Latn",
60
+ "fur_Latn",
61
+ "fuv_Latn",
62
+ "gla_Latn",
63
+ "gle_Latn",
64
+ "glg_Latn",
65
+ "grn_Latn",
66
+ "guj_Gujr",
67
+ "hat_Latn",
68
+ "hau_Latn",
69
+ "heb_Hebr",
70
+ "hin_Deva",
71
+ "hne_Deva",
72
+ "hrv_Latn",
73
+ "hun_Latn",
74
+ "hye_Armn",
75
+ "ibo_Latn",
76
+ "ilo_Latn",
77
+ "ind_Latn",
78
+ "isl_Latn",
79
+ "ita_Latn",
80
+ "jav_Latn",
81
+ "jpn_Jpan",
82
+ "kab_Latn",
83
+ "kac_Latn",
84
+ "kam_Latn",
85
+ "kan_Knda",
86
+ "kas_Arab",
87
+ "kas_Deva",
88
+ "kat_Geor",
89
+ "knc_Arab",
90
+ "knc_Latn",
91
+ "kaz_Cyrl",
92
+ "kbp_Latn",
93
+ "kea_Latn",
94
+ "khm_Khmr",
95
+ "kik_Latn",
96
+ "kin_Latn",
97
+ "kir_Cyrl",
98
+ "kmb_Latn",
99
+ "kon_Latn",
100
+ "kor_Hang",
101
+ "kmr_Latn",
102
+ "lao_Laoo",
103
+ "lvs_Latn",
104
+ "lij_Latn",
105
+ "lim_Latn",
106
+ "lin_Latn",
107
+ "lit_Latn",
108
+ "lmo_Latn",
109
+ "ltg_Latn",
110
+ "ltz_Latn",
111
+ "lua_Latn",
112
+ "lug_Latn",
113
+ "luo_Latn",
114
+ "lus_Latn",
115
+ "mag_Deva",
116
+ "mai_Deva",
117
+ "mal_Mlym",
118
+ "mar_Deva",
119
+ "min_Latn",
120
+ "mkd_Cyrl",
121
+ "plt_Latn",
122
+ "mlt_Latn",
123
+ "mni_Beng",
124
+ "khk_Cyrl",
125
+ "mos_Latn",
126
+ "mri_Latn",
127
+ "zsm_Latn",
128
+ "mya_Mymr",
129
+ "nld_Latn",
130
+ "nno_Latn",
131
+ "nob_Latn",
132
+ "npi_Deva",
133
+ "nso_Latn",
134
+ "nus_Latn",
135
+ "nya_Latn",
136
+ "oci_Latn",
137
+ "gaz_Latn",
138
+ "ory_Orya",
139
+ "pag_Latn",
140
+ "pan_Guru",
141
+ "pap_Latn",
142
+ "pol_Latn",
143
+ "por_Latn",
144
+ "prs_Arab",
145
+ "pbt_Arab",
146
+ "quy_Latn",
147
+ "ron_Latn",
148
+ "run_Latn",
149
+ "rus_Cyrl",
150
+ "sag_Latn",
151
+ "san_Deva",
152
+ "sat_Beng",
153
+ "scn_Latn",
154
+ "shn_Mymr",
155
+ "sin_Sinh",
156
+ "slk_Latn",
157
+ "slv_Latn",
158
+ "smo_Latn",
159
+ "sna_Latn",
160
+ "snd_Arab",
161
+ "som_Latn",
162
+ "sot_Latn",
163
+ "spa_Latn",
164
+ "als_Latn",
165
+ "srd_Latn",
166
+ "srp_Cyrl",
167
+ "ssw_Latn",
168
+ "sun_Latn",
169
+ "swe_Latn",
170
+ "swh_Latn",
171
+ "szl_Latn",
172
+ "tam_Taml",
173
+ "tat_Cyrl",
174
+ "tel_Telu",
175
+ "tgk_Cyrl",
176
+ "tgl_Latn",
177
+ "tha_Thai",
178
+ "tir_Ethi",
179
+ "taq_Latn",
180
+ "taq_Tfng",
181
+ "tpi_Latn",
182
+ "tsn_Latn",
183
+ "tso_Latn",
184
+ "tuk_Latn",
185
+ "tum_Latn",
186
+ "tur_Latn",
187
+ "twi_Latn",
188
+ "tzm_Tfng",
189
+ "uig_Arab",
190
+ "ukr_Cyrl",
191
+ "umb_Latn",
192
+ "urd_Arab",
193
+ "uzn_Latn",
194
+ "vec_Latn",
195
+ "vie_Latn",
196
+ "war_Latn",
197
+ "wol_Latn",
198
+ "xho_Latn",
199
+ "ydd_Hebr",
200
+ "yor_Latn",
201
+ "yue_Hant",
202
+ "zho_Hans",
203
+ "zho_Hant",
204
+ "zul_Latn"
205
  ],
206
  "bos_token": {
207
  "content": "<s>",
 
224
  "rstrip": false,
225
  "single_word": false
226
  },
227
+ "mask_token": {
228
+ "content": "<mask>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
  "pad_token": {
235
  "content": "<pad>",
236
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d13a4eb66e4ae8f1c7d9c669613d1ab49f3939e3a504137f2266089aa23bf29
3
- size 17365083
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b39b25b0763a1dd69dec54081fafcf10770d9f2538a3bd975a0c4be6d60a9c2
3
+ size 17331294
tokenizer_config.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<pad>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
@@ -10,7 +9,7 @@
10
  "special": true
11
  },
12
  "1": {
13
- "content": "<unk>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
@@ -18,7 +17,7 @@
18
  "special": true
19
  },
20
  "2": {
21
- "content": "<s>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
@@ -26,7 +25,7 @@
26
  "special": true
27
  },
28
  "3": {
29
- "content": "</s>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
@@ -34,7 +33,7 @@
34
  "special": true
35
  },
36
  "256001": {
37
- "content": "__afr__",
38
  "lstrip": false,
39
  "normalized": false,
40
  "rstrip": false,
@@ -42,7 +41,7 @@
42
  "special": true
43
  },
44
  "256002": {
45
- "content": "__amh__",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
@@ -50,7 +49,7 @@
50
  "special": true
51
  },
52
  "256003": {
53
- "content": "__arb__",
54
  "lstrip": false,
55
  "normalized": false,
56
  "rstrip": false,
@@ -58,7 +57,7 @@
58
  "special": true
59
  },
60
  "256004": {
61
- "content": "__ary__",
62
  "lstrip": false,
63
  "normalized": false,
64
  "rstrip": false,
@@ -66,7 +65,7 @@
66
  "special": true
67
  },
68
  "256005": {
69
- "content": "__arz__",
70
  "lstrip": false,
71
  "normalized": false,
72
  "rstrip": false,
@@ -74,7 +73,7 @@
74
  "special": true
75
  },
76
  "256006": {
77
- "content": "__asm__",
78
  "lstrip": false,
79
  "normalized": false,
80
  "rstrip": false,
@@ -82,7 +81,7 @@
82
  "special": true
83
  },
84
  "256007": {
85
- "content": "__azj__",
86
  "lstrip": false,
87
  "normalized": false,
88
  "rstrip": false,
@@ -90,7 +89,7 @@
90
  "special": true
91
  },
92
  "256008": {
93
- "content": "__bel__",
94
  "lstrip": false,
95
  "normalized": false,
96
  "rstrip": false,
@@ -98,7 +97,7 @@
98
  "special": true
99
  },
100
  "256009": {
101
- "content": "__ben__",
102
  "lstrip": false,
103
  "normalized": false,
104
  "rstrip": false,
@@ -106,7 +105,7 @@
106
  "special": true
107
  },
108
  "256010": {
109
- "content": "__bos__",
110
  "lstrip": false,
111
  "normalized": false,
112
  "rstrip": false,
@@ -114,7 +113,7 @@
114
  "special": true
115
  },
116
  "256011": {
117
- "content": "__bul__",
118
  "lstrip": false,
119
  "normalized": false,
120
  "rstrip": false,
@@ -122,7 +121,7 @@
122
  "special": true
123
  },
124
  "256012": {
125
- "content": "__cat__",
126
  "lstrip": false,
127
  "normalized": false,
128
  "rstrip": false,
@@ -130,7 +129,7 @@
130
  "special": true
131
  },
132
  "256013": {
133
- "content": "__ceb__",
134
  "lstrip": false,
135
  "normalized": false,
136
  "rstrip": false,
@@ -138,7 +137,7 @@
138
  "special": true
139
  },
140
  "256014": {
141
- "content": "__ces__",
142
  "lstrip": false,
143
  "normalized": false,
144
  "rstrip": false,
@@ -146,7 +145,7 @@
146
  "special": true
147
  },
148
  "256015": {
149
- "content": "__ckb__",
150
  "lstrip": false,
151
  "normalized": false,
152
  "rstrip": false,
@@ -154,7 +153,7 @@
154
  "special": true
155
  },
156
  "256016": {
157
- "content": "__cmn__",
158
  "lstrip": false,
159
  "normalized": false,
160
  "rstrip": false,
@@ -162,7 +161,7 @@
162
  "special": true
163
  },
164
  "256017": {
165
- "content": "__cmn_Hant__",
166
  "lstrip": false,
167
  "normalized": false,
168
  "rstrip": false,
@@ -170,7 +169,7 @@
170
  "special": true
171
  },
172
  "256018": {
173
- "content": "__cym__",
174
  "lstrip": false,
175
  "normalized": false,
176
  "rstrip": false,
@@ -178,7 +177,7 @@
178
  "special": true
179
  },
180
  "256019": {
181
- "content": "__dan__",
182
  "lstrip": false,
183
  "normalized": false,
184
  "rstrip": false,
@@ -186,7 +185,7 @@
186
  "special": true
187
  },
188
  "256020": {
189
- "content": "__deu__",
190
  "lstrip": false,
191
  "normalized": false,
192
  "rstrip": false,
@@ -194,7 +193,7 @@
194
  "special": true
195
  },
196
  "256021": {
197
- "content": "__ell__",
198
  "lstrip": false,
199
  "normalized": false,
200
  "rstrip": false,
@@ -202,7 +201,7 @@
202
  "special": true
203
  },
204
  "256022": {
205
- "content": "__eng__",
206
  "lstrip": false,
207
  "normalized": false,
208
  "rstrip": false,
@@ -210,7 +209,7 @@
210
  "special": true
211
  },
212
  "256023": {
213
- "content": "__est__",
214
  "lstrip": false,
215
  "normalized": false,
216
  "rstrip": false,
@@ -218,7 +217,7 @@
218
  "special": true
219
  },
220
  "256024": {
221
- "content": "__eus__",
222
  "lstrip": false,
223
  "normalized": false,
224
  "rstrip": false,
@@ -226,7 +225,7 @@
226
  "special": true
227
  },
228
  "256025": {
229
- "content": "__fin__",
230
  "lstrip": false,
231
  "normalized": false,
232
  "rstrip": false,
@@ -234,7 +233,7 @@
234
  "special": true
235
  },
236
  "256026": {
237
- "content": "__fra__",
238
  "lstrip": false,
239
  "normalized": false,
240
  "rstrip": false,
@@ -242,7 +241,7 @@
242
  "special": true
243
  },
244
  "256027": {
245
- "content": "__fuv__",
246
  "lstrip": false,
247
  "normalized": false,
248
  "rstrip": false,
@@ -250,7 +249,7 @@
250
  "special": true
251
  },
252
  "256028": {
253
- "content": "__gaz__",
254
  "lstrip": false,
255
  "normalized": false,
256
  "rstrip": false,
@@ -258,7 +257,7 @@
258
  "special": true
259
  },
260
  "256029": {
261
- "content": "__gle__",
262
  "lstrip": false,
263
  "normalized": false,
264
  "rstrip": false,
@@ -266,7 +265,7 @@
266
  "special": true
267
  },
268
  "256030": {
269
- "content": "__glg__",
270
  "lstrip": false,
271
  "normalized": false,
272
  "rstrip": false,
@@ -274,7 +273,7 @@
274
  "special": true
275
  },
276
  "256031": {
277
- "content": "__guj__",
278
  "lstrip": false,
279
  "normalized": false,
280
  "rstrip": false,
@@ -282,7 +281,7 @@
282
  "special": true
283
  },
284
  "256032": {
285
- "content": "__heb__",
286
  "lstrip": false,
287
  "normalized": false,
288
  "rstrip": false,
@@ -290,7 +289,7 @@
290
  "special": true
291
  },
292
  "256033": {
293
- "content": "__hin__",
294
  "lstrip": false,
295
  "normalized": false,
296
  "rstrip": false,
@@ -298,7 +297,7 @@
298
  "special": true
299
  },
300
  "256034": {
301
- "content": "__hrv__",
302
  "lstrip": false,
303
  "normalized": false,
304
  "rstrip": false,
@@ -306,7 +305,7 @@
306
  "special": true
307
  },
308
  "256035": {
309
- "content": "__hun__",
310
  "lstrip": false,
311
  "normalized": false,
312
  "rstrip": false,
@@ -314,7 +313,7 @@
314
  "special": true
315
  },
316
  "256036": {
317
- "content": "__hye__",
318
  "lstrip": false,
319
  "normalized": false,
320
  "rstrip": false,
@@ -322,7 +321,7 @@
322
  "special": true
323
  },
324
  "256037": {
325
- "content": "__ibo__",
326
  "lstrip": false,
327
  "normalized": false,
328
  "rstrip": false,
@@ -330,7 +329,7 @@
330
  "special": true
331
  },
332
  "256038": {
333
- "content": "__ind__",
334
  "lstrip": false,
335
  "normalized": false,
336
  "rstrip": false,
@@ -338,7 +337,7 @@
338
  "special": true
339
  },
340
  "256039": {
341
- "content": "__isl__",
342
  "lstrip": false,
343
  "normalized": false,
344
  "rstrip": false,
@@ -346,7 +345,7 @@
346
  "special": true
347
  },
348
  "256040": {
349
- "content": "__ita__",
350
  "lstrip": false,
351
  "normalized": false,
352
  "rstrip": false,
@@ -354,7 +353,7 @@
354
  "special": true
355
  },
356
  "256041": {
357
- "content": "__jav__",
358
  "lstrip": false,
359
  "normalized": false,
360
  "rstrip": false,
@@ -362,7 +361,7 @@
362
  "special": true
363
  },
364
  "256042": {
365
- "content": "__jpn__",
366
  "lstrip": false,
367
  "normalized": false,
368
  "rstrip": false,
@@ -370,7 +369,7 @@
370
  "special": true
371
  },
372
  "256043": {
373
- "content": "__kan__",
374
  "lstrip": false,
375
  "normalized": false,
376
  "rstrip": false,
@@ -378,7 +377,7 @@
378
  "special": true
379
  },
380
  "256044": {
381
- "content": "__kat__",
382
  "lstrip": false,
383
  "normalized": false,
384
  "rstrip": false,
@@ -386,7 +385,7 @@
386
  "special": true
387
  },
388
  "256045": {
389
- "content": "__kaz__",
390
  "lstrip": false,
391
  "normalized": false,
392
  "rstrip": false,
@@ -394,7 +393,7 @@
394
  "special": true
395
  },
396
  "256046": {
397
- "content": "__khk__",
398
  "lstrip": false,
399
  "normalized": false,
400
  "rstrip": false,
@@ -402,7 +401,7 @@
402
  "special": true
403
  },
404
  "256047": {
405
- "content": "__khm__",
406
  "lstrip": false,
407
  "normalized": false,
408
  "rstrip": false,
@@ -410,7 +409,7 @@
410
  "special": true
411
  },
412
  "256048": {
413
- "content": "__kir__",
414
  "lstrip": false,
415
  "normalized": false,
416
  "rstrip": false,
@@ -418,7 +417,7 @@
418
  "special": true
419
  },
420
  "256049": {
421
- "content": "__kor__",
422
  "lstrip": false,
423
  "normalized": false,
424
  "rstrip": false,
@@ -426,7 +425,7 @@
426
  "special": true
427
  },
428
  "256050": {
429
- "content": "__lao__",
430
  "lstrip": false,
431
  "normalized": false,
432
  "rstrip": false,
@@ -434,7 +433,7 @@
434
  "special": true
435
  },
436
  "256051": {
437
- "content": "__lit__",
438
  "lstrip": false,
439
  "normalized": false,
440
  "rstrip": false,
@@ -442,7 +441,7 @@
442
  "special": true
443
  },
444
  "256052": {
445
- "content": "__lug__",
446
  "lstrip": false,
447
  "normalized": false,
448
  "rstrip": false,
@@ -450,7 +449,7 @@
450
  "special": true
451
  },
452
  "256053": {
453
- "content": "__luo__",
454
  "lstrip": false,
455
  "normalized": false,
456
  "rstrip": false,
@@ -458,7 +457,7 @@
458
  "special": true
459
  },
460
  "256054": {
461
- "content": "__lvs__",
462
  "lstrip": false,
463
  "normalized": false,
464
  "rstrip": false,
@@ -466,7 +465,7 @@
466
  "special": true
467
  },
468
  "256055": {
469
- "content": "__mai__",
470
  "lstrip": false,
471
  "normalized": false,
472
  "rstrip": false,
@@ -474,7 +473,7 @@
474
  "special": true
475
  },
476
  "256056": {
477
- "content": "__mal__",
478
  "lstrip": false,
479
  "normalized": false,
480
  "rstrip": false,
@@ -482,7 +481,7 @@
482
  "special": true
483
  },
484
  "256057": {
485
- "content": "__mar__",
486
  "lstrip": false,
487
  "normalized": false,
488
  "rstrip": false,
@@ -490,7 +489,7 @@
490
  "special": true
491
  },
492
  "256058": {
493
- "content": "__mkd__",
494
  "lstrip": false,
495
  "normalized": false,
496
  "rstrip": false,
@@ -498,7 +497,7 @@
498
  "special": true
499
  },
500
  "256059": {
501
- "content": "__mlt__",
502
  "lstrip": false,
503
  "normalized": false,
504
  "rstrip": false,
@@ -506,7 +505,7 @@
506
  "special": true
507
  },
508
  "256060": {
509
- "content": "__mni__",
510
  "lstrip": false,
511
  "normalized": false,
512
  "rstrip": false,
@@ -514,7 +513,7 @@
514
  "special": true
515
  },
516
  "256061": {
517
- "content": "__mya__",
518
  "lstrip": false,
519
  "normalized": false,
520
  "rstrip": false,
@@ -522,7 +521,7 @@
522
  "special": true
523
  },
524
  "256062": {
525
- "content": "__nld__",
526
  "lstrip": false,
527
  "normalized": false,
528
  "rstrip": false,
@@ -530,7 +529,7 @@
530
  "special": true
531
  },
532
  "256063": {
533
- "content": "__nno__",
534
  "lstrip": false,
535
  "normalized": false,
536
  "rstrip": false,
@@ -538,7 +537,7 @@
538
  "special": true
539
  },
540
  "256064": {
541
- "content": "__nob__",
542
  "lstrip": false,
543
  "normalized": false,
544
  "rstrip": false,
@@ -546,7 +545,7 @@
546
  "special": true
547
  },
548
  "256065": {
549
- "content": "__npi__",
550
  "lstrip": false,
551
  "normalized": false,
552
  "rstrip": false,
@@ -554,7 +553,7 @@
554
  "special": true
555
  },
556
  "256066": {
557
- "content": "__nya__",
558
  "lstrip": false,
559
  "normalized": false,
560
  "rstrip": false,
@@ -562,7 +561,7 @@
562
  "special": true
563
  },
564
  "256067": {
565
- "content": "__ory__",
566
  "lstrip": false,
567
  "normalized": false,
568
  "rstrip": false,
@@ -570,7 +569,7 @@
570
  "special": true
571
  },
572
  "256068": {
573
- "content": "__pan__",
574
  "lstrip": false,
575
  "normalized": false,
576
  "rstrip": false,
@@ -578,7 +577,7 @@
578
  "special": true
579
  },
580
  "256069": {
581
- "content": "__pbt__",
582
  "lstrip": false,
583
  "normalized": false,
584
  "rstrip": false,
@@ -586,7 +585,7 @@
586
  "special": true
587
  },
588
  "256070": {
589
- "content": "__pes__",
590
  "lstrip": false,
591
  "normalized": false,
592
  "rstrip": false,
@@ -594,7 +593,7 @@
594
  "special": true
595
  },
596
  "256071": {
597
- "content": "__pol__",
598
  "lstrip": false,
599
  "normalized": false,
600
  "rstrip": false,
@@ -602,7 +601,7 @@
602
  "special": true
603
  },
604
  "256072": {
605
- "content": "__por__",
606
  "lstrip": false,
607
  "normalized": false,
608
  "rstrip": false,
@@ -610,7 +609,7 @@
610
  "special": true
611
  },
612
  "256073": {
613
- "content": "__ron__",
614
  "lstrip": false,
615
  "normalized": false,
616
  "rstrip": false,
@@ -618,7 +617,7 @@
618
  "special": true
619
  },
620
  "256074": {
621
- "content": "__rus__",
622
  "lstrip": false,
623
  "normalized": false,
624
  "rstrip": false,
@@ -626,7 +625,7 @@
626
  "special": true
627
  },
628
  "256075": {
629
- "content": "__sat__",
630
  "lstrip": false,
631
  "normalized": false,
632
  "rstrip": false,
@@ -634,7 +633,7 @@
634
  "special": true
635
  },
636
  "256076": {
637
- "content": "__slk__",
638
  "lstrip": false,
639
  "normalized": false,
640
  "rstrip": false,
@@ -642,7 +641,7 @@
642
  "special": true
643
  },
644
  "256077": {
645
- "content": "__slv__",
646
  "lstrip": false,
647
  "normalized": false,
648
  "rstrip": false,
@@ -650,7 +649,7 @@
650
  "special": true
651
  },
652
  "256078": {
653
- "content": "__sna__",
654
  "lstrip": false,
655
  "normalized": false,
656
  "rstrip": false,
@@ -658,7 +657,7 @@
658
  "special": true
659
  },
660
  "256079": {
661
- "content": "__snd__",
662
  "lstrip": false,
663
  "normalized": false,
664
  "rstrip": false,
@@ -666,7 +665,7 @@
666
  "special": true
667
  },
668
  "256080": {
669
- "content": "__som__",
670
  "lstrip": false,
671
  "normalized": false,
672
  "rstrip": false,
@@ -674,7 +673,7 @@
674
  "special": true
675
  },
676
  "256081": {
677
- "content": "__spa__",
678
  "lstrip": false,
679
  "normalized": false,
680
  "rstrip": false,
@@ -682,7 +681,7 @@
682
  "special": true
683
  },
684
  "256082": {
685
- "content": "__srp__",
686
  "lstrip": false,
687
  "normalized": false,
688
  "rstrip": false,
@@ -690,7 +689,7 @@
690
  "special": true
691
  },
692
  "256083": {
693
- "content": "__swe__",
694
  "lstrip": false,
695
  "normalized": false,
696
  "rstrip": false,
@@ -698,7 +697,7 @@
698
  "special": true
699
  },
700
  "256084": {
701
- "content": "__swh__",
702
  "lstrip": false,
703
  "normalized": false,
704
  "rstrip": false,
@@ -706,7 +705,7 @@
706
  "special": true
707
  },
708
  "256085": {
709
- "content": "__tam__",
710
  "lstrip": false,
711
  "normalized": false,
712
  "rstrip": false,
@@ -714,7 +713,7 @@
714
  "special": true
715
  },
716
  "256086": {
717
- "content": "__tel__",
718
  "lstrip": false,
719
  "normalized": false,
720
  "rstrip": false,
@@ -722,7 +721,7 @@
722
  "special": true
723
  },
724
  "256087": {
725
- "content": "__tgk__",
726
  "lstrip": false,
727
  "normalized": false,
728
  "rstrip": false,
@@ -730,7 +729,7 @@
730
  "special": true
731
  },
732
  "256088": {
733
- "content": "__tgl__",
734
  "lstrip": false,
735
  "normalized": false,
736
  "rstrip": false,
@@ -738,7 +737,7 @@
738
  "special": true
739
  },
740
  "256089": {
741
- "content": "__tha__",
742
  "lstrip": false,
743
  "normalized": false,
744
  "rstrip": false,
@@ -746,7 +745,7 @@
746
  "special": true
747
  },
748
  "256090": {
749
- "content": "__tur__",
750
  "lstrip": false,
751
  "normalized": false,
752
  "rstrip": false,
@@ -754,7 +753,7 @@
754
  "special": true
755
  },
756
  "256091": {
757
- "content": "__ukr__",
758
  "lstrip": false,
759
  "normalized": false,
760
  "rstrip": false,
@@ -762,7 +761,7 @@
762
  "special": true
763
  },
764
  "256092": {
765
- "content": "__urd__",
766
  "lstrip": false,
767
  "normalized": false,
768
  "rstrip": false,
@@ -770,7 +769,7 @@
770
  "special": true
771
  },
772
  "256093": {
773
- "content": "__uzn__",
774
  "lstrip": false,
775
  "normalized": false,
776
  "rstrip": false,
@@ -778,7 +777,7 @@
778
  "special": true
779
  },
780
  "256094": {
781
- "content": "__vie__",
782
  "lstrip": false,
783
  "normalized": false,
784
  "rstrip": false,
@@ -786,7 +785,7 @@
786
  "special": true
787
  },
788
  "256095": {
789
- "content": "__yor__",
790
  "lstrip": false,
791
  "normalized": false,
792
  "rstrip": false,
@@ -794,7 +793,7 @@
794
  "special": true
795
  },
796
  "256096": {
797
- "content": "__yue__",
798
  "lstrip": false,
799
  "normalized": false,
800
  "rstrip": false,
@@ -802,7 +801,7 @@
802
  "special": true
803
  },
804
  "256097": {
805
- "content": "__zlm__",
806
  "lstrip": false,
807
  "normalized": false,
808
  "rstrip": false,
@@ -810,125 +809,1070 @@
810
  "special": true
811
  },
812
  "256098": {
813
- "content": "__zul__",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
814
  "lstrip": false,
815
  "normalized": false,
816
  "rstrip": false,
817
  "single_word": false,
818
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
819
  }
820
  },
821
  "additional_special_tokens": [
822
- "__afr__",
823
- "__amh__",
824
- "__arb__",
825
- "__ary__",
826
- "__arz__",
827
- "__asm__",
828
- "__azj__",
829
- "__bel__",
830
- "__ben__",
831
- "__bos__",
832
- "__bul__",
833
- "__cat__",
834
- "__ceb__",
835
- "__ces__",
836
- "__ckb__",
837
- "__cmn__",
838
- "__cmn_Hant__",
839
- "__cym__",
840
- "__dan__",
841
- "__deu__",
842
- "__ell__",
843
- "__eng__",
844
- "__est__",
845
- "__eus__",
846
- "__fin__",
847
- "__fra__",
848
- "__fuv__",
849
- "__gaz__",
850
- "__gle__",
851
- "__glg__",
852
- "__guj__",
853
- "__heb__",
854
- "__hin__",
855
- "__hrv__",
856
- "__hun__",
857
- "__hye__",
858
- "__ibo__",
859
- "__ind__",
860
- "__isl__",
861
- "__ita__",
862
- "__jav__",
863
- "__jpn__",
864
- "__kan__",
865
- "__kat__",
866
- "__kaz__",
867
- "__khk__",
868
- "__khm__",
869
- "__kir__",
870
- "__kor__",
871
- "__lao__",
872
- "__lit__",
873
- "__lug__",
874
- "__luo__",
875
- "__lvs__",
876
- "__mai__",
877
- "__mal__",
878
- "__mar__",
879
- "__mkd__",
880
- "__mlt__",
881
- "__mni__",
882
- "__mya__",
883
- "__nld__",
884
- "__nno__",
885
- "__nob__",
886
- "__npi__",
887
- "__nya__",
888
- "__ory__",
889
- "__pan__",
890
- "__pbt__",
891
- "__pes__",
892
- "__pol__",
893
- "__por__",
894
- "__ron__",
895
- "__rus__",
896
- "__sat__",
897
- "__slk__",
898
- "__slv__",
899
- "__sna__",
900
- "__snd__",
901
- "__som__",
902
- "__spa__",
903
- "__srp__",
904
- "__swe__",
905
- "__swh__",
906
- "__tam__",
907
- "__tel__",
908
- "__tgk__",
909
- "__tgl__",
910
- "__tha__",
911
- "__tur__",
912
- "__ukr__",
913
- "__urd__",
914
- "__uzn__",
915
- "__vie__",
916
- "__yor__",
917
- "__yue__",
918
- "__zlm__",
919
- "__zul__"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
920
  ],
921
  "bos_token": "<s>",
922
  "clean_up_tokenization_spaces": true,
923
  "cls_token": "<s>",
924
  "eos_token": "</s>",
925
- "model_max_length": 1000000000000000019884624838656,
 
 
926
  "pad_token": "<pad>",
927
- "processor_class": "SeamlessM4TProcessor",
928
  "sep_token": "</s>",
929
  "sp_model_kwargs": {},
930
- "src_lang": "__eng__",
931
- "tgt_lang": "__fra__",
932
- "tokenizer_class": "SeamlessM4TTokenizer",
933
  "unk_token": "<unk>"
934
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "<pad>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "</s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "3": {
28
+ "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
 
33
  "special": true
34
  },
35
  "256001": {
36
+ "content": "ace_Arab",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
41
  "special": true
42
  },
43
  "256002": {
44
+ "content": "ace_Latn",
45
  "lstrip": false,
46
  "normalized": false,
47
  "rstrip": false,
 
49
  "special": true
50
  },
51
  "256003": {
52
+ "content": "acm_Arab",
53
  "lstrip": false,
54
  "normalized": false,
55
  "rstrip": false,
 
57
  "special": true
58
  },
59
  "256004": {
60
+ "content": "acq_Arab",
61
  "lstrip": false,
62
  "normalized": false,
63
  "rstrip": false,
 
65
  "special": true
66
  },
67
  "256005": {
68
+ "content": "aeb_Arab",
69
  "lstrip": false,
70
  "normalized": false,
71
  "rstrip": false,
 
73
  "special": true
74
  },
75
  "256006": {
76
+ "content": "afr_Latn",
77
  "lstrip": false,
78
  "normalized": false,
79
  "rstrip": false,
 
81
  "special": true
82
  },
83
  "256007": {
84
+ "content": "ajp_Arab",
85
  "lstrip": false,
86
  "normalized": false,
87
  "rstrip": false,
 
89
  "special": true
90
  },
91
  "256008": {
92
+ "content": "aka_Latn",
93
  "lstrip": false,
94
  "normalized": false,
95
  "rstrip": false,
 
97
  "special": true
98
  },
99
  "256009": {
100
+ "content": "amh_Ethi",
101
  "lstrip": false,
102
  "normalized": false,
103
  "rstrip": false,
 
105
  "special": true
106
  },
107
  "256010": {
108
+ "content": "apc_Arab",
109
  "lstrip": false,
110
  "normalized": false,
111
  "rstrip": false,
 
113
  "special": true
114
  },
115
  "256011": {
116
+ "content": "arb_Arab",
117
  "lstrip": false,
118
  "normalized": false,
119
  "rstrip": false,
 
121
  "special": true
122
  },
123
  "256012": {
124
+ "content": "ars_Arab",
125
  "lstrip": false,
126
  "normalized": false,
127
  "rstrip": false,
 
129
  "special": true
130
  },
131
  "256013": {
132
+ "content": "ary_Arab",
133
  "lstrip": false,
134
  "normalized": false,
135
  "rstrip": false,
 
137
  "special": true
138
  },
139
  "256014": {
140
+ "content": "arz_Arab",
141
  "lstrip": false,
142
  "normalized": false,
143
  "rstrip": false,
 
145
  "special": true
146
  },
147
  "256015": {
148
+ "content": "asm_Beng",
149
  "lstrip": false,
150
  "normalized": false,
151
  "rstrip": false,
 
153
  "special": true
154
  },
155
  "256016": {
156
+ "content": "ast_Latn",
157
  "lstrip": false,
158
  "normalized": false,
159
  "rstrip": false,
 
161
  "special": true
162
  },
163
  "256017": {
164
+ "content": "awa_Deva",
165
  "lstrip": false,
166
  "normalized": false,
167
  "rstrip": false,
 
169
  "special": true
170
  },
171
  "256018": {
172
+ "content": "ayr_Latn",
173
  "lstrip": false,
174
  "normalized": false,
175
  "rstrip": false,
 
177
  "special": true
178
  },
179
  "256019": {
180
+ "content": "azb_Arab",
181
  "lstrip": false,
182
  "normalized": false,
183
  "rstrip": false,
 
185
  "special": true
186
  },
187
  "256020": {
188
+ "content": "azj_Latn",
189
  "lstrip": false,
190
  "normalized": false,
191
  "rstrip": false,
 
193
  "special": true
194
  },
195
  "256021": {
196
+ "content": "bak_Cyrl",
197
  "lstrip": false,
198
  "normalized": false,
199
  "rstrip": false,
 
201
  "special": true
202
  },
203
  "256022": {
204
+ "content": "bam_Latn",
205
  "lstrip": false,
206
  "normalized": false,
207
  "rstrip": false,
 
209
  "special": true
210
  },
211
  "256023": {
212
+ "content": "ban_Latn",
213
  "lstrip": false,
214
  "normalized": false,
215
  "rstrip": false,
 
217
  "special": true
218
  },
219
  "256024": {
220
+ "content": "bel_Cyrl",
221
  "lstrip": false,
222
  "normalized": false,
223
  "rstrip": false,
 
225
  "special": true
226
  },
227
  "256025": {
228
+ "content": "bem_Latn",
229
  "lstrip": false,
230
  "normalized": false,
231
  "rstrip": false,
 
233
  "special": true
234
  },
235
  "256026": {
236
+ "content": "ben_Beng",
237
  "lstrip": false,
238
  "normalized": false,
239
  "rstrip": false,
 
241
  "special": true
242
  },
243
  "256027": {
244
+ "content": "bho_Deva",
245
  "lstrip": false,
246
  "normalized": false,
247
  "rstrip": false,
 
249
  "special": true
250
  },
251
  "256028": {
252
+ "content": "bjn_Arab",
253
  "lstrip": false,
254
  "normalized": false,
255
  "rstrip": false,
 
257
  "special": true
258
  },
259
  "256029": {
260
+ "content": "bjn_Latn",
261
  "lstrip": false,
262
  "normalized": false,
263
  "rstrip": false,
 
265
  "special": true
266
  },
267
  "256030": {
268
+ "content": "bod_Tibt",
269
  "lstrip": false,
270
  "normalized": false,
271
  "rstrip": false,
 
273
  "special": true
274
  },
275
  "256031": {
276
+ "content": "bos_Latn",
277
  "lstrip": false,
278
  "normalized": false,
279
  "rstrip": false,
 
281
  "special": true
282
  },
283
  "256032": {
284
+ "content": "bug_Latn",
285
  "lstrip": false,
286
  "normalized": false,
287
  "rstrip": false,
 
289
  "special": true
290
  },
291
  "256033": {
292
+ "content": "bul_Cyrl",
293
  "lstrip": false,
294
  "normalized": false,
295
  "rstrip": false,
 
297
  "special": true
298
  },
299
  "256034": {
300
+ "content": "cat_Latn",
301
  "lstrip": false,
302
  "normalized": false,
303
  "rstrip": false,
 
305
  "special": true
306
  },
307
  "256035": {
308
+ "content": "ceb_Latn",
309
  "lstrip": false,
310
  "normalized": false,
311
  "rstrip": false,
 
313
  "special": true
314
  },
315
  "256036": {
316
+ "content": "ces_Latn",
317
  "lstrip": false,
318
  "normalized": false,
319
  "rstrip": false,
 
321
  "special": true
322
  },
323
  "256037": {
324
+ "content": "cjk_Latn",
325
  "lstrip": false,
326
  "normalized": false,
327
  "rstrip": false,
 
329
  "special": true
330
  },
331
  "256038": {
332
+ "content": "ckb_Arab",
333
  "lstrip": false,
334
  "normalized": false,
335
  "rstrip": false,
 
337
  "special": true
338
  },
339
  "256039": {
340
+ "content": "crh_Latn",
341
  "lstrip": false,
342
  "normalized": false,
343
  "rstrip": false,
 
345
  "special": true
346
  },
347
  "256040": {
348
+ "content": "cym_Latn",
349
  "lstrip": false,
350
  "normalized": false,
351
  "rstrip": false,
 
353
  "special": true
354
  },
355
  "256041": {
356
+ "content": "dan_Latn",
357
  "lstrip": false,
358
  "normalized": false,
359
  "rstrip": false,
 
361
  "special": true
362
  },
363
  "256042": {
364
+ "content": "deu_Latn",
365
  "lstrip": false,
366
  "normalized": false,
367
  "rstrip": false,
 
369
  "special": true
370
  },
371
  "256043": {
372
+ "content": "dik_Latn",
373
  "lstrip": false,
374
  "normalized": false,
375
  "rstrip": false,
 
377
  "special": true
378
  },
379
  "256044": {
380
+ "content": "dyu_Latn",
381
  "lstrip": false,
382
  "normalized": false,
383
  "rstrip": false,
 
385
  "special": true
386
  },
387
  "256045": {
388
+ "content": "dzo_Tibt",
389
  "lstrip": false,
390
  "normalized": false,
391
  "rstrip": false,
 
393
  "special": true
394
  },
395
  "256046": {
396
+ "content": "ell_Grek",
397
  "lstrip": false,
398
  "normalized": false,
399
  "rstrip": false,
 
401
  "special": true
402
  },
403
  "256047": {
404
+ "content": "eng_Latn",
405
  "lstrip": false,
406
  "normalized": false,
407
  "rstrip": false,
 
409
  "special": true
410
  },
411
  "256048": {
412
+ "content": "epo_Latn",
413
  "lstrip": false,
414
  "normalized": false,
415
  "rstrip": false,
 
417
  "special": true
418
  },
419
  "256049": {
420
+ "content": "est_Latn",
421
  "lstrip": false,
422
  "normalized": false,
423
  "rstrip": false,
 
425
  "special": true
426
  },
427
  "256050": {
428
+ "content": "eus_Latn",
429
  "lstrip": false,
430
  "normalized": false,
431
  "rstrip": false,
 
433
  "special": true
434
  },
435
  "256051": {
436
+ "content": "ewe_Latn",
437
  "lstrip": false,
438
  "normalized": false,
439
  "rstrip": false,
 
441
  "special": true
442
  },
443
  "256052": {
444
+ "content": "fao_Latn",
445
  "lstrip": false,
446
  "normalized": false,
447
  "rstrip": false,
 
449
  "special": true
450
  },
451
  "256053": {
452
+ "content": "pes_Arab",
453
  "lstrip": false,
454
  "normalized": false,
455
  "rstrip": false,
 
457
  "special": true
458
  },
459
  "256054": {
460
+ "content": "fij_Latn",
461
  "lstrip": false,
462
  "normalized": false,
463
  "rstrip": false,
 
465
  "special": true
466
  },
467
  "256055": {
468
+ "content": "fin_Latn",
469
  "lstrip": false,
470
  "normalized": false,
471
  "rstrip": false,
 
473
  "special": true
474
  },
475
  "256056": {
476
+ "content": "fon_Latn",
477
  "lstrip": false,
478
  "normalized": false,
479
  "rstrip": false,
 
481
  "special": true
482
  },
483
  "256057": {
484
+ "content": "fra_Latn",
485
  "lstrip": false,
486
  "normalized": false,
487
  "rstrip": false,
 
489
  "special": true
490
  },
491
  "256058": {
492
+ "content": "fur_Latn",
493
  "lstrip": false,
494
  "normalized": false,
495
  "rstrip": false,
 
497
  "special": true
498
  },
499
  "256059": {
500
+ "content": "fuv_Latn",
501
  "lstrip": false,
502
  "normalized": false,
503
  "rstrip": false,
 
505
  "special": true
506
  },
507
  "256060": {
508
+ "content": "gla_Latn",
509
  "lstrip": false,
510
  "normalized": false,
511
  "rstrip": false,
 
513
  "special": true
514
  },
515
  "256061": {
516
+ "content": "gle_Latn",
517
  "lstrip": false,
518
  "normalized": false,
519
  "rstrip": false,
 
521
  "special": true
522
  },
523
  "256062": {
524
+ "content": "glg_Latn",
525
  "lstrip": false,
526
  "normalized": false,
527
  "rstrip": false,
 
529
  "special": true
530
  },
531
  "256063": {
532
+ "content": "grn_Latn",
533
  "lstrip": false,
534
  "normalized": false,
535
  "rstrip": false,
 
537
  "special": true
538
  },
539
  "256064": {
540
+ "content": "guj_Gujr",
541
  "lstrip": false,
542
  "normalized": false,
543
  "rstrip": false,
 
545
  "special": true
546
  },
547
  "256065": {
548
+ "content": "hat_Latn",
549
  "lstrip": false,
550
  "normalized": false,
551
  "rstrip": false,
 
553
  "special": true
554
  },
555
  "256066": {
556
+ "content": "hau_Latn",
557
  "lstrip": false,
558
  "normalized": false,
559
  "rstrip": false,
 
561
  "special": true
562
  },
563
  "256067": {
564
+ "content": "heb_Hebr",
565
  "lstrip": false,
566
  "normalized": false,
567
  "rstrip": false,
 
569
  "special": true
570
  },
571
  "256068": {
572
+ "content": "hin_Deva",
573
  "lstrip": false,
574
  "normalized": false,
575
  "rstrip": false,
 
577
  "special": true
578
  },
579
  "256069": {
580
+ "content": "hne_Deva",
581
  "lstrip": false,
582
  "normalized": false,
583
  "rstrip": false,
 
585
  "special": true
586
  },
587
  "256070": {
588
+ "content": "hrv_Latn",
589
  "lstrip": false,
590
  "normalized": false,
591
  "rstrip": false,
 
593
  "special": true
594
  },
595
  "256071": {
596
+ "content": "hun_Latn",
597
  "lstrip": false,
598
  "normalized": false,
599
  "rstrip": false,
 
601
  "special": true
602
  },
603
  "256072": {
604
+ "content": "hye_Armn",
605
  "lstrip": false,
606
  "normalized": false,
607
  "rstrip": false,
 
609
  "special": true
610
  },
611
  "256073": {
612
+ "content": "ibo_Latn",
613
  "lstrip": false,
614
  "normalized": false,
615
  "rstrip": false,
 
617
  "special": true
618
  },
619
  "256074": {
620
+ "content": "ilo_Latn",
621
  "lstrip": false,
622
  "normalized": false,
623
  "rstrip": false,
 
625
  "special": true
626
  },
627
  "256075": {
628
+ "content": "ind_Latn",
629
  "lstrip": false,
630
  "normalized": false,
631
  "rstrip": false,
 
633
  "special": true
634
  },
635
  "256076": {
636
+ "content": "isl_Latn",
637
  "lstrip": false,
638
  "normalized": false,
639
  "rstrip": false,
 
641
  "special": true
642
  },
643
  "256077": {
644
+ "content": "ita_Latn",
645
  "lstrip": false,
646
  "normalized": false,
647
  "rstrip": false,
 
649
  "special": true
650
  },
651
  "256078": {
652
+ "content": "jav_Latn",
653
  "lstrip": false,
654
  "normalized": false,
655
  "rstrip": false,
 
657
  "special": true
658
  },
659
  "256079": {
660
+ "content": "jpn_Jpan",
661
  "lstrip": false,
662
  "normalized": false,
663
  "rstrip": false,
 
665
  "special": true
666
  },
667
  "256080": {
668
+ "content": "kab_Latn",
669
  "lstrip": false,
670
  "normalized": false,
671
  "rstrip": false,
 
673
  "special": true
674
  },
675
  "256081": {
676
+ "content": "kac_Latn",
677
  "lstrip": false,
678
  "normalized": false,
679
  "rstrip": false,
 
681
  "special": true
682
  },
683
  "256082": {
684
+ "content": "kam_Latn",
685
  "lstrip": false,
686
  "normalized": false,
687
  "rstrip": false,
 
689
  "special": true
690
  },
691
  "256083": {
692
+ "content": "kan_Knda",
693
  "lstrip": false,
694
  "normalized": false,
695
  "rstrip": false,
 
697
  "special": true
698
  },
699
  "256084": {
700
+ "content": "kas_Arab",
701
  "lstrip": false,
702
  "normalized": false,
703
  "rstrip": false,
 
705
  "special": true
706
  },
707
  "256085": {
708
+ "content": "kas_Deva",
709
  "lstrip": false,
710
  "normalized": false,
711
  "rstrip": false,
 
713
  "special": true
714
  },
715
  "256086": {
716
+ "content": "kat_Geor",
717
  "lstrip": false,
718
  "normalized": false,
719
  "rstrip": false,
 
721
  "special": true
722
  },
723
  "256087": {
724
+ "content": "knc_Arab",
725
  "lstrip": false,
726
  "normalized": false,
727
  "rstrip": false,
 
729
  "special": true
730
  },
731
  "256088": {
732
+ "content": "knc_Latn",
733
  "lstrip": false,
734
  "normalized": false,
735
  "rstrip": false,
 
737
  "special": true
738
  },
739
  "256089": {
740
+ "content": "kaz_Cyrl",
741
  "lstrip": false,
742
  "normalized": false,
743
  "rstrip": false,
 
745
  "special": true
746
  },
747
  "256090": {
748
+ "content": "kbp_Latn",
749
  "lstrip": false,
750
  "normalized": false,
751
  "rstrip": false,
 
753
  "special": true
754
  },
755
  "256091": {
756
+ "content": "kea_Latn",
757
  "lstrip": false,
758
  "normalized": false,
759
  "rstrip": false,
 
761
  "special": true
762
  },
763
  "256092": {
764
+ "content": "khm_Khmr",
765
  "lstrip": false,
766
  "normalized": false,
767
  "rstrip": false,
 
769
  "special": true
770
  },
771
  "256093": {
772
+ "content": "kik_Latn",
773
  "lstrip": false,
774
  "normalized": false,
775
  "rstrip": false,
 
777
  "special": true
778
  },
779
  "256094": {
780
+ "content": "kin_Latn",
781
  "lstrip": false,
782
  "normalized": false,
783
  "rstrip": false,
 
785
  "special": true
786
  },
787
  "256095": {
788
+ "content": "kir_Cyrl",
789
  "lstrip": false,
790
  "normalized": false,
791
  "rstrip": false,
 
793
  "special": true
794
  },
795
  "256096": {
796
+ "content": "kmb_Latn",
797
  "lstrip": false,
798
  "normalized": false,
799
  "rstrip": false,
 
801
  "special": true
802
  },
803
  "256097": {
804
+ "content": "kon_Latn",
805
  "lstrip": false,
806
  "normalized": false,
807
  "rstrip": false,
 
809
  "special": true
810
  },
811
  "256098": {
812
+ "content": "kor_Hang",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "256099": {
820
+ "content": "kmr_Latn",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "256100": {
828
+ "content": "lao_Laoo",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "256101": {
836
+ "content": "lvs_Latn",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "256102": {
844
+ "content": "lij_Latn",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "256103": {
852
+ "content": "lim_Latn",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "256104": {
860
+ "content": "lin_Latn",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "256105": {
868
+ "content": "lit_Latn",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "256106": {
876
+ "content": "lmo_Latn",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "256107": {
884
+ "content": "ltg_Latn",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "256108": {
892
+ "content": "ltz_Latn",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "256109": {
900
+ "content": "lua_Latn",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "256110": {
908
+ "content": "lug_Latn",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "256111": {
916
+ "content": "luo_Latn",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "256112": {
924
+ "content": "lus_Latn",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "256113": {
932
+ "content": "mag_Deva",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "256114": {
940
+ "content": "mai_Deva",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "256115": {
948
+ "content": "mal_Mlym",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "256116": {
956
+ "content": "mar_Deva",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "256117": {
964
+ "content": "min_Latn",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "256118": {
972
+ "content": "mkd_Cyrl",
973
  "lstrip": false,
974
  "normalized": false,
975
  "rstrip": false,
976
  "single_word": false,
977
  "special": true
978
+ },
979
+ "256119": {
980
+ "content": "plt_Latn",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "256120": {
988
+ "content": "mlt_Latn",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "256121": {
996
+ "content": "mni_Beng",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "256122": {
1004
+ "content": "khk_Cyrl",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "256123": {
1012
+ "content": "mos_Latn",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "256124": {
1020
+ "content": "mri_Latn",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "256125": {
1028
+ "content": "zsm_Latn",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "256126": {
1036
+ "content": "mya_Mymr",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "256127": {
1044
+ "content": "nld_Latn",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "256128": {
1052
+ "content": "nno_Latn",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "256129": {
1060
+ "content": "nob_Latn",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "256130": {
1068
+ "content": "npi_Deva",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "256131": {
1076
+ "content": "nso_Latn",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "256132": {
1084
+ "content": "nus_Latn",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "256133": {
1092
+ "content": "nya_Latn",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "256134": {
1100
+ "content": "oci_Latn",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "256135": {
1108
+ "content": "gaz_Latn",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "256136": {
1116
+ "content": "ory_Orya",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "256137": {
1124
+ "content": "pag_Latn",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "256138": {
1132
+ "content": "pan_Guru",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "256139": {
1140
+ "content": "pap_Latn",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "256140": {
1148
+ "content": "pol_Latn",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "256141": {
1156
+ "content": "por_Latn",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "256142": {
1164
+ "content": "prs_Arab",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "256143": {
1172
+ "content": "pbt_Arab",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "256144": {
1180
+ "content": "quy_Latn",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "256145": {
1188
+ "content": "ron_Latn",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "256146": {
1196
+ "content": "run_Latn",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "256147": {
1204
+ "content": "rus_Cyrl",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "256148": {
1212
+ "content": "sag_Latn",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "256149": {
1220
+ "content": "san_Deva",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "256150": {
1228
+ "content": "sat_Beng",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "256151": {
1236
+ "content": "scn_Latn",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "256152": {
1244
+ "content": "shn_Mymr",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "256153": {
1252
+ "content": "sin_Sinh",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "256154": {
1260
+ "content": "slk_Latn",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "256155": {
1268
+ "content": "slv_Latn",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "256156": {
1276
+ "content": "smo_Latn",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "256157": {
1284
+ "content": "sna_Latn",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "256158": {
1292
+ "content": "snd_Arab",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "256159": {
1300
+ "content": "som_Latn",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "256160": {
1308
+ "content": "sot_Latn",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "256161": {
1316
+ "content": "spa_Latn",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "256162": {
1324
+ "content": "als_Latn",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "256163": {
1332
+ "content": "srd_Latn",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "256164": {
1340
+ "content": "srp_Cyrl",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "256165": {
1348
+ "content": "ssw_Latn",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "256166": {
1356
+ "content": "sun_Latn",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "256167": {
1364
+ "content": "swe_Latn",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "256168": {
1372
+ "content": "swh_Latn",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "256169": {
1380
+ "content": "szl_Latn",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "256170": {
1388
+ "content": "tam_Taml",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "256171": {
1396
+ "content": "tat_Cyrl",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "256172": {
1404
+ "content": "tel_Telu",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "256173": {
1412
+ "content": "tgk_Cyrl",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "256174": {
1420
+ "content": "tgl_Latn",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "256175": {
1428
+ "content": "tha_Thai",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "256176": {
1436
+ "content": "tir_Ethi",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "256177": {
1444
+ "content": "taq_Latn",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "256178": {
1452
+ "content": "taq_Tfng",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "256179": {
1460
+ "content": "tpi_Latn",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "256180": {
1468
+ "content": "tsn_Latn",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "256181": {
1476
+ "content": "tso_Latn",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "256182": {
1484
+ "content": "tuk_Latn",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "256183": {
1492
+ "content": "tum_Latn",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "256184": {
1500
+ "content": "tur_Latn",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "256185": {
1508
+ "content": "twi_Latn",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "256186": {
1516
+ "content": "tzm_Tfng",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "256187": {
1524
+ "content": "uig_Arab",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "256188": {
1532
+ "content": "ukr_Cyrl",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "256189": {
1540
+ "content": "umb_Latn",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "256190": {
1548
+ "content": "urd_Arab",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "256191": {
1556
+ "content": "uzn_Latn",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "256192": {
1564
+ "content": "vec_Latn",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "256193": {
1572
+ "content": "vie_Latn",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "256194": {
1580
+ "content": "war_Latn",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "256195": {
1588
+ "content": "wol_Latn",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "256196": {
1596
+ "content": "xho_Latn",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "256197": {
1604
+ "content": "ydd_Hebr",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "256198": {
1612
+ "content": "yor_Latn",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "256199": {
1620
+ "content": "yue_Hant",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "256200": {
1628
+ "content": "zho_Hans",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "256201": {
1636
+ "content": "zho_Hant",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "256202": {
1644
+ "content": "zul_Latn",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "256203": {
1652
+ "content": "<mask>",
1653
+ "lstrip": true,
1654
+ "normalized": true,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
  }
1659
  },
1660
  "additional_special_tokens": [
1661
+ "ace_Arab",
1662
+ "ace_Latn",
1663
+ "acm_Arab",
1664
+ "acq_Arab",
1665
+ "aeb_Arab",
1666
+ "afr_Latn",
1667
+ "ajp_Arab",
1668
+ "aka_Latn",
1669
+ "amh_Ethi",
1670
+ "apc_Arab",
1671
+ "arb_Arab",
1672
+ "ars_Arab",
1673
+ "ary_Arab",
1674
+ "arz_Arab",
1675
+ "asm_Beng",
1676
+ "ast_Latn",
1677
+ "awa_Deva",
1678
+ "ayr_Latn",
1679
+ "azb_Arab",
1680
+ "azj_Latn",
1681
+ "bak_Cyrl",
1682
+ "bam_Latn",
1683
+ "ban_Latn",
1684
+ "bel_Cyrl",
1685
+ "bem_Latn",
1686
+ "ben_Beng",
1687
+ "bho_Deva",
1688
+ "bjn_Arab",
1689
+ "bjn_Latn",
1690
+ "bod_Tibt",
1691
+ "bos_Latn",
1692
+ "bug_Latn",
1693
+ "bul_Cyrl",
1694
+ "cat_Latn",
1695
+ "ceb_Latn",
1696
+ "ces_Latn",
1697
+ "cjk_Latn",
1698
+ "ckb_Arab",
1699
+ "crh_Latn",
1700
+ "cym_Latn",
1701
+ "dan_Latn",
1702
+ "deu_Latn",
1703
+ "dik_Latn",
1704
+ "dyu_Latn",
1705
+ "dzo_Tibt",
1706
+ "ell_Grek",
1707
+ "eng_Latn",
1708
+ "epo_Latn",
1709
+ "est_Latn",
1710
+ "eus_Latn",
1711
+ "ewe_Latn",
1712
+ "fao_Latn",
1713
+ "pes_Arab",
1714
+ "fij_Latn",
1715
+ "fin_Latn",
1716
+ "fon_Latn",
1717
+ "fra_Latn",
1718
+ "fur_Latn",
1719
+ "fuv_Latn",
1720
+ "gla_Latn",
1721
+ "gle_Latn",
1722
+ "glg_Latn",
1723
+ "grn_Latn",
1724
+ "guj_Gujr",
1725
+ "hat_Latn",
1726
+ "hau_Latn",
1727
+ "heb_Hebr",
1728
+ "hin_Deva",
1729
+ "hne_Deva",
1730
+ "hrv_Latn",
1731
+ "hun_Latn",
1732
+ "hye_Armn",
1733
+ "ibo_Latn",
1734
+ "ilo_Latn",
1735
+ "ind_Latn",
1736
+ "isl_Latn",
1737
+ "ita_Latn",
1738
+ "jav_Latn",
1739
+ "jpn_Jpan",
1740
+ "kab_Latn",
1741
+ "kac_Latn",
1742
+ "kam_Latn",
1743
+ "kan_Knda",
1744
+ "kas_Arab",
1745
+ "kas_Deva",
1746
+ "kat_Geor",
1747
+ "knc_Arab",
1748
+ "knc_Latn",
1749
+ "kaz_Cyrl",
1750
+ "kbp_Latn",
1751
+ "kea_Latn",
1752
+ "khm_Khmr",
1753
+ "kik_Latn",
1754
+ "kin_Latn",
1755
+ "kir_Cyrl",
1756
+ "kmb_Latn",
1757
+ "kon_Latn",
1758
+ "kor_Hang",
1759
+ "kmr_Latn",
1760
+ "lao_Laoo",
1761
+ "lvs_Latn",
1762
+ "lij_Latn",
1763
+ "lim_Latn",
1764
+ "lin_Latn",
1765
+ "lit_Latn",
1766
+ "lmo_Latn",
1767
+ "ltg_Latn",
1768
+ "ltz_Latn",
1769
+ "lua_Latn",
1770
+ "lug_Latn",
1771
+ "luo_Latn",
1772
+ "lus_Latn",
1773
+ "mag_Deva",
1774
+ "mai_Deva",
1775
+ "mal_Mlym",
1776
+ "mar_Deva",
1777
+ "min_Latn",
1778
+ "mkd_Cyrl",
1779
+ "plt_Latn",
1780
+ "mlt_Latn",
1781
+ "mni_Beng",
1782
+ "khk_Cyrl",
1783
+ "mos_Latn",
1784
+ "mri_Latn",
1785
+ "zsm_Latn",
1786
+ "mya_Mymr",
1787
+ "nld_Latn",
1788
+ "nno_Latn",
1789
+ "nob_Latn",
1790
+ "npi_Deva",
1791
+ "nso_Latn",
1792
+ "nus_Latn",
1793
+ "nya_Latn",
1794
+ "oci_Latn",
1795
+ "gaz_Latn",
1796
+ "ory_Orya",
1797
+ "pag_Latn",
1798
+ "pan_Guru",
1799
+ "pap_Latn",
1800
+ "pol_Latn",
1801
+ "por_Latn",
1802
+ "prs_Arab",
1803
+ "pbt_Arab",
1804
+ "quy_Latn",
1805
+ "ron_Latn",
1806
+ "run_Latn",
1807
+ "rus_Cyrl",
1808
+ "sag_Latn",
1809
+ "san_Deva",
1810
+ "sat_Beng",
1811
+ "scn_Latn",
1812
+ "shn_Mymr",
1813
+ "sin_Sinh",
1814
+ "slk_Latn",
1815
+ "slv_Latn",
1816
+ "smo_Latn",
1817
+ "sna_Latn",
1818
+ "snd_Arab",
1819
+ "som_Latn",
1820
+ "sot_Latn",
1821
+ "spa_Latn",
1822
+ "als_Latn",
1823
+ "srd_Latn",
1824
+ "srp_Cyrl",
1825
+ "ssw_Latn",
1826
+ "sun_Latn",
1827
+ "swe_Latn",
1828
+ "swh_Latn",
1829
+ "szl_Latn",
1830
+ "tam_Taml",
1831
+ "tat_Cyrl",
1832
+ "tel_Telu",
1833
+ "tgk_Cyrl",
1834
+ "tgl_Latn",
1835
+ "tha_Thai",
1836
+ "tir_Ethi",
1837
+ "taq_Latn",
1838
+ "taq_Tfng",
1839
+ "tpi_Latn",
1840
+ "tsn_Latn",
1841
+ "tso_Latn",
1842
+ "tuk_Latn",
1843
+ "tum_Latn",
1844
+ "tur_Latn",
1845
+ "twi_Latn",
1846
+ "tzm_Tfng",
1847
+ "uig_Arab",
1848
+ "ukr_Cyrl",
1849
+ "umb_Latn",
1850
+ "urd_Arab",
1851
+ "uzn_Latn",
1852
+ "vec_Latn",
1853
+ "vie_Latn",
1854
+ "war_Latn",
1855
+ "wol_Latn",
1856
+ "xho_Latn",
1857
+ "ydd_Hebr",
1858
+ "yor_Latn",
1859
+ "yue_Hant",
1860
+ "zho_Hans",
1861
+ "zho_Hant",
1862
+ "zul_Latn"
1863
  ],
1864
  "bos_token": "<s>",
1865
  "clean_up_tokenization_spaces": true,
1866
  "cls_token": "<s>",
1867
  "eos_token": "</s>",
1868
+ "legacy_behaviour": false,
1869
+ "mask_token": "<mask>",
1870
+ "model_max_length": 1024,
1871
  "pad_token": "<pad>",
 
1872
  "sep_token": "</s>",
1873
  "sp_model_kwargs": {},
1874
+ "src_lang": "eng_Latn",
1875
+ "tgt_lang": null,
1876
+ "tokenizer_class": "NllbTokenizer",
1877
  "unk_token": "<unk>"
1878
  }