ylacombe HF staff commited on
Commit
94be387
1 Parent(s): 622d133

Upload processor (#7)

Browse files

- Upload processor (452815af55f5b8b0ab6cd76de9a481fc7c7159f8)

Files changed (3) hide show
  1. added_tokens.json +107 -0
  2. special_tokens_map.json +111 -0
  3. tokenizer_config.json +945 -1
added_tokens.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 3,
3
+ "<MINED_DATA>": 256099,
4
+ "<MMT_BT_DATA>": 256100,
5
+ "<SMT_BT_DATA>": 256101,
6
+ "<pad>": 0,
7
+ "<s>": 2,
8
+ "<unk>": 1,
9
+ "__afr__": 256001,
10
+ "__amh__": 256002,
11
+ "__arb__": 256003,
12
+ "__ary__": 256004,
13
+ "__arz__": 256005,
14
+ "__asm__": 256006,
15
+ "__azj__": 256007,
16
+ "__bel__": 256008,
17
+ "__ben__": 256009,
18
+ "__bos__": 256010,
19
+ "__bul__": 256011,
20
+ "__cat__": 256012,
21
+ "__ceb__": 256013,
22
+ "__ces__": 256014,
23
+ "__ckb__": 256015,
24
+ "__cmn_Hant__": 256017,
25
+ "__cmn__": 256016,
26
+ "__cym__": 256018,
27
+ "__dan__": 256019,
28
+ "__deu__": 256020,
29
+ "__ell__": 256021,
30
+ "__eng__": 256022,
31
+ "__est__": 256023,
32
+ "__eus__": 256024,
33
+ "__fin__": 256025,
34
+ "__fra__": 256026,
35
+ "__fuv__": 256027,
36
+ "__gaz__": 256028,
37
+ "__gle__": 256029,
38
+ "__glg__": 256030,
39
+ "__guj__": 256031,
40
+ "__heb__": 256032,
41
+ "__hin__": 256033,
42
+ "__hrv__": 256034,
43
+ "__hun__": 256035,
44
+ "__hye__": 256036,
45
+ "__ibo__": 256037,
46
+ "__ind__": 256038,
47
+ "__isl__": 256039,
48
+ "__ita__": 256040,
49
+ "__jav__": 256041,
50
+ "__jpn__": 256042,
51
+ "__kan__": 256043,
52
+ "__kat__": 256044,
53
+ "__kaz__": 256045,
54
+ "__khk__": 256046,
55
+ "__khm__": 256047,
56
+ "__kir__": 256048,
57
+ "__kor__": 256049,
58
+ "__lao__": 256050,
59
+ "__lit__": 256051,
60
+ "__lug__": 256052,
61
+ "__luo__": 256053,
62
+ "__lvs__": 256054,
63
+ "__mai__": 256055,
64
+ "__mal__": 256056,
65
+ "__mar__": 256057,
66
+ "__mkd__": 256058,
67
+ "__mlt__": 256059,
68
+ "__mni__": 256060,
69
+ "__mya__": 256061,
70
+ "__nld__": 256062,
71
+ "__nno__": 256063,
72
+ "__nob__": 256064,
73
+ "__npi__": 256065,
74
+ "__nya__": 256066,
75
+ "__ory__": 256067,
76
+ "__pan__": 256068,
77
+ "__pbt__": 256069,
78
+ "__pes__": 256070,
79
+ "__pol__": 256071,
80
+ "__por__": 256072,
81
+ "__ron__": 256073,
82
+ "__rus__": 256074,
83
+ "__sat__": 256075,
84
+ "__slk__": 256076,
85
+ "__slv__": 256077,
86
+ "__sna__": 256078,
87
+ "__snd__": 256079,
88
+ "__som__": 256080,
89
+ "__spa__": 256081,
90
+ "__srp__": 256082,
91
+ "__swe__": 256083,
92
+ "__swh__": 256084,
93
+ "__tam__": 256085,
94
+ "__tel__": 256086,
95
+ "__tgk__": 256087,
96
+ "__tgl__": 256088,
97
+ "__tha__": 256089,
98
+ "__tur__": 256090,
99
+ "__ukr__": 256091,
100
+ "__urd__": 256092,
101
+ "__uzn__": 256093,
102
+ "__vie__": 256094,
103
+ "__yor__": 256095,
104
+ "__yue__": 256096,
105
+ "__zlm__": 256097,
106
+ "__zul__": 256098
107
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<MINED_DATA>",
102
+ "<MMT_BT_DATA>",
103
+ "<SMT_BT_DATA>"
104
+ ],
105
+ "bos_token": "<s>",
106
+ "cls_token": "<s>",
107
+ "eos_token": "</s>",
108
+ "pad_token": "<pad>",
109
+ "sep_token": "</s>",
110
+ "unk_token": "<unk>"
111
+ }
tokenizer_config.json CHANGED
@@ -1,5 +1,949 @@
1
  {
2
- "additional_special_tokens": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
  "cls_token": "<s>",
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "256001": {
36
+ "content": "__afr__",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "256002": {
44
+ "content": "__amh__",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "256003": {
52
+ "content": "__arb__",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "256004": {
60
+ "content": "__ary__",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "256005": {
68
+ "content": "__arz__",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "256006": {
76
+ "content": "__asm__",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "256007": {
84
+ "content": "__azj__",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "256008": {
92
+ "content": "__bel__",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "256009": {
100
+ "content": "__ben__",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "256010": {
108
+ "content": "__bos__",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "256011": {
116
+ "content": "__bul__",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "256012": {
124
+ "content": "__cat__",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "256013": {
132
+ "content": "__ceb__",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "256014": {
140
+ "content": "__ces__",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "256015": {
148
+ "content": "__ckb__",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "256016": {
156
+ "content": "__cmn__",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "256017": {
164
+ "content": "__cmn_Hant__",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "256018": {
172
+ "content": "__cym__",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "256019": {
180
+ "content": "__dan__",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "256020": {
188
+ "content": "__deu__",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "256021": {
196
+ "content": "__ell__",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "256022": {
204
+ "content": "__eng__",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "256023": {
212
+ "content": "__est__",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "256024": {
220
+ "content": "__eus__",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "256025": {
228
+ "content": "__fin__",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "256026": {
236
+ "content": "__fra__",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "256027": {
244
+ "content": "__fuv__",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "256028": {
252
+ "content": "__gaz__",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "256029": {
260
+ "content": "__gle__",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "256030": {
268
+ "content": "__glg__",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "256031": {
276
+ "content": "__guj__",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "256032": {
284
+ "content": "__heb__",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "256033": {
292
+ "content": "__hin__",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "256034": {
300
+ "content": "__hrv__",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "256035": {
308
+ "content": "__hun__",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "256036": {
316
+ "content": "__hye__",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "256037": {
324
+ "content": "__ibo__",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "256038": {
332
+ "content": "__ind__",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "256039": {
340
+ "content": "__isl__",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "256040": {
348
+ "content": "__ita__",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "256041": {
356
+ "content": "__jav__",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "256042": {
364
+ "content": "__jpn__",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "256043": {
372
+ "content": "__kan__",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "256044": {
380
+ "content": "__kat__",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "256045": {
388
+ "content": "__kaz__",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "256046": {
396
+ "content": "__khk__",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "256047": {
404
+ "content": "__khm__",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "256048": {
412
+ "content": "__kir__",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "256049": {
420
+ "content": "__kor__",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "256050": {
428
+ "content": "__lao__",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "256051": {
436
+ "content": "__lit__",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "256052": {
444
+ "content": "__lug__",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "256053": {
452
+ "content": "__luo__",
453
+ "lstrip": true,
454
+ "normalized": false,
455
+ "rstrip": true,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "256054": {
460
+ "content": "__lvs__",
461
+ "lstrip": true,
462
+ "normalized": false,
463
+ "rstrip": true,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "256055": {
468
+ "content": "__mai__",
469
+ "lstrip": true,
470
+ "normalized": false,
471
+ "rstrip": true,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "256056": {
476
+ "content": "__mal__",
477
+ "lstrip": true,
478
+ "normalized": false,
479
+ "rstrip": true,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "256057": {
484
+ "content": "__mar__",
485
+ "lstrip": true,
486
+ "normalized": false,
487
+ "rstrip": true,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "256058": {
492
+ "content": "__mkd__",
493
+ "lstrip": true,
494
+ "normalized": false,
495
+ "rstrip": true,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "256059": {
500
+ "content": "__mlt__",
501
+ "lstrip": true,
502
+ "normalized": false,
503
+ "rstrip": true,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "256060": {
508
+ "content": "__mni__",
509
+ "lstrip": true,
510
+ "normalized": false,
511
+ "rstrip": true,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "256061": {
516
+ "content": "__mya__",
517
+ "lstrip": true,
518
+ "normalized": false,
519
+ "rstrip": true,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "256062": {
524
+ "content": "__nld__",
525
+ "lstrip": true,
526
+ "normalized": false,
527
+ "rstrip": true,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "256063": {
532
+ "content": "__nno__",
533
+ "lstrip": true,
534
+ "normalized": false,
535
+ "rstrip": true,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "256064": {
540
+ "content": "__nob__",
541
+ "lstrip": true,
542
+ "normalized": false,
543
+ "rstrip": true,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "256065": {
548
+ "content": "__npi__",
549
+ "lstrip": true,
550
+ "normalized": false,
551
+ "rstrip": true,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "256066": {
556
+ "content": "__nya__",
557
+ "lstrip": true,
558
+ "normalized": false,
559
+ "rstrip": true,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "256067": {
564
+ "content": "__ory__",
565
+ "lstrip": true,
566
+ "normalized": false,
567
+ "rstrip": true,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "256068": {
572
+ "content": "__pan__",
573
+ "lstrip": true,
574
+ "normalized": false,
575
+ "rstrip": true,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "256069": {
580
+ "content": "__pbt__",
581
+ "lstrip": true,
582
+ "normalized": false,
583
+ "rstrip": true,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "256070": {
588
+ "content": "__pes__",
589
+ "lstrip": true,
590
+ "normalized": false,
591
+ "rstrip": true,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "256071": {
596
+ "content": "__pol__",
597
+ "lstrip": true,
598
+ "normalized": false,
599
+ "rstrip": true,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "256072": {
604
+ "content": "__por__",
605
+ "lstrip": true,
606
+ "normalized": false,
607
+ "rstrip": true,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "256073": {
612
+ "content": "__ron__",
613
+ "lstrip": true,
614
+ "normalized": false,
615
+ "rstrip": true,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "256074": {
620
+ "content": "__rus__",
621
+ "lstrip": true,
622
+ "normalized": false,
623
+ "rstrip": true,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "256075": {
628
+ "content": "__sat__",
629
+ "lstrip": true,
630
+ "normalized": false,
631
+ "rstrip": true,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "256076": {
636
+ "content": "__slk__",
637
+ "lstrip": true,
638
+ "normalized": false,
639
+ "rstrip": true,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "256077": {
644
+ "content": "__slv__",
645
+ "lstrip": true,
646
+ "normalized": false,
647
+ "rstrip": true,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "256078": {
652
+ "content": "__sna__",
653
+ "lstrip": true,
654
+ "normalized": false,
655
+ "rstrip": true,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "256079": {
660
+ "content": "__snd__",
661
+ "lstrip": true,
662
+ "normalized": false,
663
+ "rstrip": true,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "256080": {
668
+ "content": "__som__",
669
+ "lstrip": true,
670
+ "normalized": false,
671
+ "rstrip": true,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "256081": {
676
+ "content": "__spa__",
677
+ "lstrip": true,
678
+ "normalized": false,
679
+ "rstrip": true,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "256082": {
684
+ "content": "__srp__",
685
+ "lstrip": true,
686
+ "normalized": false,
687
+ "rstrip": true,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "256083": {
692
+ "content": "__swe__",
693
+ "lstrip": true,
694
+ "normalized": false,
695
+ "rstrip": true,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "256084": {
700
+ "content": "__swh__",
701
+ "lstrip": true,
702
+ "normalized": false,
703
+ "rstrip": true,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "256085": {
708
+ "content": "__tam__",
709
+ "lstrip": true,
710
+ "normalized": false,
711
+ "rstrip": true,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "256086": {
716
+ "content": "__tel__",
717
+ "lstrip": true,
718
+ "normalized": false,
719
+ "rstrip": true,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "256087": {
724
+ "content": "__tgk__",
725
+ "lstrip": true,
726
+ "normalized": false,
727
+ "rstrip": true,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "256088": {
732
+ "content": "__tgl__",
733
+ "lstrip": true,
734
+ "normalized": false,
735
+ "rstrip": true,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "256089": {
740
+ "content": "__tha__",
741
+ "lstrip": true,
742
+ "normalized": false,
743
+ "rstrip": true,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "256090": {
748
+ "content": "__tur__",
749
+ "lstrip": true,
750
+ "normalized": false,
751
+ "rstrip": true,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "256091": {
756
+ "content": "__ukr__",
757
+ "lstrip": true,
758
+ "normalized": false,
759
+ "rstrip": true,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "256092": {
764
+ "content": "__urd__",
765
+ "lstrip": true,
766
+ "normalized": false,
767
+ "rstrip": true,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "256093": {
772
+ "content": "__uzn__",
773
+ "lstrip": true,
774
+ "normalized": false,
775
+ "rstrip": true,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "256094": {
780
+ "content": "__vie__",
781
+ "lstrip": true,
782
+ "normalized": false,
783
+ "rstrip": true,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "256095": {
788
+ "content": "__yor__",
789
+ "lstrip": true,
790
+ "normalized": false,
791
+ "rstrip": true,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "256096": {
796
+ "content": "__yue__",
797
+ "lstrip": true,
798
+ "normalized": false,
799
+ "rstrip": true,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "256097": {
804
+ "content": "__zlm__",
805
+ "lstrip": true,
806
+ "normalized": false,
807
+ "rstrip": true,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "256098": {
812
+ "content": "__zul__",
813
+ "lstrip": true,
814
+ "normalized": false,
815
+ "rstrip": true,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "256099": {
820
+ "content": "<MINED_DATA>",
821
+ "lstrip": true,
822
+ "normalized": false,
823
+ "rstrip": true,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "256100": {
828
+ "content": "<MMT_BT_DATA>",
829
+ "lstrip": true,
830
+ "normalized": false,
831
+ "rstrip": true,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "256101": {
836
+ "content": "<SMT_BT_DATA>",
837
+ "lstrip": true,
838
+ "normalized": false,
839
+ "rstrip": true,
840
+ "single_word": false,
841
+ "special": true
842
+ }
843
+ },
844
+ "additional_special_tokens": [
845
+ "__afr__",
846
+ "__amh__",
847
+ "__arb__",
848
+ "__ary__",
849
+ "__arz__",
850
+ "__asm__",
851
+ "__azj__",
852
+ "__bel__",
853
+ "__ben__",
854
+ "__bos__",
855
+ "__bul__",
856
+ "__cat__",
857
+ "__ceb__",
858
+ "__ces__",
859
+ "__ckb__",
860
+ "__cmn__",
861
+ "__cmn_Hant__",
862
+ "__cym__",
863
+ "__dan__",
864
+ "__deu__",
865
+ "__ell__",
866
+ "__eng__",
867
+ "__est__",
868
+ "__eus__",
869
+ "__fin__",
870
+ "__fra__",
871
+ "__fuv__",
872
+ "__gaz__",
873
+ "__gle__",
874
+ "__glg__",
875
+ "__guj__",
876
+ "__heb__",
877
+ "__hin__",
878
+ "__hrv__",
879
+ "__hun__",
880
+ "__hye__",
881
+ "__ibo__",
882
+ "__ind__",
883
+ "__isl__",
884
+ "__ita__",
885
+ "__jav__",
886
+ "__jpn__",
887
+ "__kan__",
888
+ "__kat__",
889
+ "__kaz__",
890
+ "__khk__",
891
+ "__khm__",
892
+ "__kir__",
893
+ "__kor__",
894
+ "__lao__",
895
+ "__lit__",
896
+ "__lug__",
897
+ "__luo__",
898
+ "__lvs__",
899
+ "__mai__",
900
+ "__mal__",
901
+ "__mar__",
902
+ "__mkd__",
903
+ "__mlt__",
904
+ "__mni__",
905
+ "__mya__",
906
+ "__nld__",
907
+ "__nno__",
908
+ "__nob__",
909
+ "__npi__",
910
+ "__nya__",
911
+ "__ory__",
912
+ "__pan__",
913
+ "__pbt__",
914
+ "__pes__",
915
+ "__pol__",
916
+ "__por__",
917
+ "__ron__",
918
+ "__rus__",
919
+ "__sat__",
920
+ "__slk__",
921
+ "__slv__",
922
+ "__sna__",
923
+ "__snd__",
924
+ "__som__",
925
+ "__spa__",
926
+ "__srp__",
927
+ "__swe__",
928
+ "__swh__",
929
+ "__tam__",
930
+ "__tel__",
931
+ "__tgk__",
932
+ "__tgl__",
933
+ "__tha__",
934
+ "__tur__",
935
+ "__ukr__",
936
+ "__urd__",
937
+ "__uzn__",
938
+ "__vie__",
939
+ "__yor__",
940
+ "__yue__",
941
+ "__zlm__",
942
+ "__zul__",
943
+ "<MINED_DATA>",
944
+ "<MMT_BT_DATA>",
945
+ "<SMT_BT_DATA>"
946
+ ],
947
  "bos_token": "<s>",
948
  "clean_up_tokenization_spaces": true,
949
  "cls_token": "<s>",