Upload tokenizer
Browse files- added_tokens.json +41 -2
- special_tokens_map.json +41 -2
- tokenizer.json +359 -8
- tokenizer_config.json +355 -4
added_tokens.json
CHANGED
@@ -1,4 +1,43 @@
|
|
1 |
{
|
2 |
-
"<
|
3 |
-
"<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"<af>": 64001,
|
3 |
+
"<am>": 64002,
|
4 |
+
"<ar>": 64003,
|
5 |
+
"<ast>": 64004,
|
6 |
+
"<be>": 64005,
|
7 |
+
"<bg>": 64006,
|
8 |
+
"<bn>": 64007,
|
9 |
+
"<bs>": 64008,
|
10 |
+
"<ca>": 64009,
|
11 |
+
"<cs>": 64010,
|
12 |
+
"<da>": 64011,
|
13 |
+
"<de>": 64012,
|
14 |
+
"<en>": 64013,
|
15 |
+
"<es>": 64014,
|
16 |
+
"<fr>": 64015,
|
17 |
+
"<gu>": 64016,
|
18 |
+
"<ha>": 64017,
|
19 |
+
"<he>": 64018,
|
20 |
+
"<hi>": 64019,
|
21 |
+
"<is>": 64020,
|
22 |
+
"<it>": 64021,
|
23 |
+
"<kab>": 64022,
|
24 |
+
"<kn>": 64023,
|
25 |
+
"<lb>": 64024,
|
26 |
+
"<mr>": 64025,
|
27 |
+
"<mt>": 64026,
|
28 |
+
"<ne>": 64027,
|
29 |
+
"<nl>": 64028,
|
30 |
+
"<no>": 64029,
|
31 |
+
"<oc>": 64030,
|
32 |
+
"<pl>": 64031,
|
33 |
+
"<pt>": 64032,
|
34 |
+
"<ro>": 64033,
|
35 |
+
"<ru>": 64034,
|
36 |
+
"<sd>": 64035,
|
37 |
+
"<so>": 64036,
|
38 |
+
"<sr>": 64037,
|
39 |
+
"<sv>": 64038,
|
40 |
+
"<ti>": 64039,
|
41 |
+
"<uk>": 64040,
|
42 |
+
"<ur>": 64041
|
43 |
}
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,46 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
"<
|
4 |
-
"<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
],
|
6 |
"bos_token": {
|
7 |
"content": "<s>",
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
"<af>",
|
4 |
+
"<am>",
|
5 |
+
"<ar>",
|
6 |
+
"<ast>",
|
7 |
+
"<be>",
|
8 |
+
"<bg>",
|
9 |
+
"<bn>",
|
10 |
+
"<bs>",
|
11 |
+
"<ca>",
|
12 |
+
"<cs>",
|
13 |
+
"<da>",
|
14 |
+
"<de>",
|
15 |
+
"<en>",
|
16 |
+
"<es>",
|
17 |
+
"<fr>",
|
18 |
+
"<gu>",
|
19 |
+
"<ha>",
|
20 |
+
"<he>",
|
21 |
+
"<hi>",
|
22 |
+
"<is>",
|
23 |
+
"<it>",
|
24 |
+
"<kab>",
|
25 |
+
"<kn>",
|
26 |
+
"<lb>",
|
27 |
+
"<mr>",
|
28 |
+
"<mt>",
|
29 |
+
"<ne>",
|
30 |
+
"<nl>",
|
31 |
+
"<no>",
|
32 |
+
"<oc>",
|
33 |
+
"<pl>",
|
34 |
+
"<pt>",
|
35 |
+
"<ro>",
|
36 |
+
"<ru>",
|
37 |
+
"<sd>",
|
38 |
+
"<so>",
|
39 |
+
"<sr>",
|
40 |
+
"<sv>",
|
41 |
+
"<ti>",
|
42 |
+
"<uk>",
|
43 |
+
"<ur>"
|
44 |
],
|
45 |
"bos_token": {
|
46 |
"content": "<s>",
|
tokenizer.json
CHANGED
@@ -41,7 +41,7 @@
|
|
41 |
},
|
42 |
{
|
43 |
"id": 64001,
|
44 |
-
"content": "<
|
45 |
"single_word": false,
|
46 |
"lstrip": false,
|
47 |
"rstrip": false,
|
@@ -50,7 +50,358 @@
|
|
50 |
},
|
51 |
{
|
52 |
"id": 64002,
|
53 |
-
"content": "<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
"single_word": false,
|
55 |
"lstrip": false,
|
56 |
"rstrip": false,
|
@@ -90,7 +441,7 @@
|
|
90 |
"single": [
|
91 |
{
|
92 |
"SpecialToken": {
|
93 |
-
"id": "<
|
94 |
"type_id": 0
|
95 |
}
|
96 |
},
|
@@ -110,7 +461,7 @@
|
|
110 |
"pair": [
|
111 |
{
|
112 |
"SpecialToken": {
|
113 |
-
"id": "<
|
114 |
"type_id": 0
|
115 |
}
|
116 |
},
|
@@ -143,13 +494,13 @@
|
|
143 |
"</s>"
|
144 |
]
|
145 |
},
|
146 |
-
"<
|
147 |
-
"id": "<
|
148 |
"ids": [
|
149 |
-
|
150 |
],
|
151 |
"tokens": [
|
152 |
-
"<
|
153 |
]
|
154 |
}
|
155 |
}
|
|
|
41 |
},
|
42 |
{
|
43 |
"id": 64001,
|
44 |
+
"content": "<af>",
|
45 |
"single_word": false,
|
46 |
"lstrip": false,
|
47 |
"rstrip": false,
|
|
|
50 |
},
|
51 |
{
|
52 |
"id": 64002,
|
53 |
+
"content": "<am>",
|
54 |
+
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"id": 64003,
|
62 |
+
"content": "<ar>",
|
63 |
+
"single_word": false,
|
64 |
+
"lstrip": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"normalized": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"id": 64004,
|
71 |
+
"content": "<ast>",
|
72 |
+
"single_word": false,
|
73 |
+
"lstrip": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"normalized": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"id": 64005,
|
80 |
+
"content": "<be>",
|
81 |
+
"single_word": false,
|
82 |
+
"lstrip": false,
|
83 |
+
"rstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"special": true
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"id": 64006,
|
89 |
+
"content": "<bg>",
|
90 |
+
"single_word": false,
|
91 |
+
"lstrip": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"normalized": false,
|
94 |
+
"special": true
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"id": 64007,
|
98 |
+
"content": "<bn>",
|
99 |
+
"single_word": false,
|
100 |
+
"lstrip": false,
|
101 |
+
"rstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"special": true
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"id": 64008,
|
107 |
+
"content": "<bs>",
|
108 |
+
"single_word": false,
|
109 |
+
"lstrip": false,
|
110 |
+
"rstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"special": true
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"id": 64009,
|
116 |
+
"content": "<ca>",
|
117 |
+
"single_word": false,
|
118 |
+
"lstrip": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"id": 64010,
|
125 |
+
"content": "<cs>",
|
126 |
+
"single_word": false,
|
127 |
+
"lstrip": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"id": 64011,
|
134 |
+
"content": "<da>",
|
135 |
+
"single_word": false,
|
136 |
+
"lstrip": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"normalized": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"id": 64012,
|
143 |
+
"content": "<de>",
|
144 |
+
"single_word": false,
|
145 |
+
"lstrip": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"normalized": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"id": 64013,
|
152 |
+
"content": "<en>",
|
153 |
+
"single_word": false,
|
154 |
+
"lstrip": false,
|
155 |
+
"rstrip": false,
|
156 |
+
"normalized": false,
|
157 |
+
"special": true
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"id": 64014,
|
161 |
+
"content": "<es>",
|
162 |
+
"single_word": false,
|
163 |
+
"lstrip": false,
|
164 |
+
"rstrip": false,
|
165 |
+
"normalized": false,
|
166 |
+
"special": true
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"id": 64015,
|
170 |
+
"content": "<fr>",
|
171 |
+
"single_word": false,
|
172 |
+
"lstrip": false,
|
173 |
+
"rstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"special": true
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"id": 64016,
|
179 |
+
"content": "<gu>",
|
180 |
+
"single_word": false,
|
181 |
+
"lstrip": false,
|
182 |
+
"rstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"special": true
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"id": 64017,
|
188 |
+
"content": "<ha>",
|
189 |
+
"single_word": false,
|
190 |
+
"lstrip": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"id": 64018,
|
197 |
+
"content": "<he>",
|
198 |
+
"single_word": false,
|
199 |
+
"lstrip": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"id": 64019,
|
206 |
+
"content": "<hi>",
|
207 |
+
"single_word": false,
|
208 |
+
"lstrip": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"normalized": false,
|
211 |
+
"special": true
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"id": 64020,
|
215 |
+
"content": "<is>",
|
216 |
+
"single_word": false,
|
217 |
+
"lstrip": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"normalized": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"id": 64021,
|
224 |
+
"content": "<it>",
|
225 |
+
"single_word": false,
|
226 |
+
"lstrip": false,
|
227 |
+
"rstrip": false,
|
228 |
+
"normalized": false,
|
229 |
+
"special": true
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"id": 64022,
|
233 |
+
"content": "<kab>",
|
234 |
+
"single_word": false,
|
235 |
+
"lstrip": false,
|
236 |
+
"rstrip": false,
|
237 |
+
"normalized": false,
|
238 |
+
"special": true
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"id": 64023,
|
242 |
+
"content": "<kn>",
|
243 |
+
"single_word": false,
|
244 |
+
"lstrip": false,
|
245 |
+
"rstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"special": true
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"id": 64024,
|
251 |
+
"content": "<lb>",
|
252 |
+
"single_word": false,
|
253 |
+
"lstrip": false,
|
254 |
+
"rstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"special": true
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"id": 64025,
|
260 |
+
"content": "<mr>",
|
261 |
+
"single_word": false,
|
262 |
+
"lstrip": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"normalized": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"id": 64026,
|
269 |
+
"content": "<mt>",
|
270 |
+
"single_word": false,
|
271 |
+
"lstrip": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"id": 64027,
|
278 |
+
"content": "<ne>",
|
279 |
+
"single_word": false,
|
280 |
+
"lstrip": false,
|
281 |
+
"rstrip": false,
|
282 |
+
"normalized": false,
|
283 |
+
"special": true
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"id": 64028,
|
287 |
+
"content": "<nl>",
|
288 |
+
"single_word": false,
|
289 |
+
"lstrip": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"normalized": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"id": 64029,
|
296 |
+
"content": "<no>",
|
297 |
+
"single_word": false,
|
298 |
+
"lstrip": false,
|
299 |
+
"rstrip": false,
|
300 |
+
"normalized": false,
|
301 |
+
"special": true
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"id": 64030,
|
305 |
+
"content": "<oc>",
|
306 |
+
"single_word": false,
|
307 |
+
"lstrip": false,
|
308 |
+
"rstrip": false,
|
309 |
+
"normalized": false,
|
310 |
+
"special": true
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"id": 64031,
|
314 |
+
"content": "<pl>",
|
315 |
+
"single_word": false,
|
316 |
+
"lstrip": false,
|
317 |
+
"rstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"special": true
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"id": 64032,
|
323 |
+
"content": "<pt>",
|
324 |
+
"single_word": false,
|
325 |
+
"lstrip": false,
|
326 |
+
"rstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"special": true
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"id": 64033,
|
332 |
+
"content": "<ro>",
|
333 |
+
"single_word": false,
|
334 |
+
"lstrip": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"normalized": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"id": 64034,
|
341 |
+
"content": "<ru>",
|
342 |
+
"single_word": false,
|
343 |
+
"lstrip": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"id": 64035,
|
350 |
+
"content": "<sd>",
|
351 |
+
"single_word": false,
|
352 |
+
"lstrip": false,
|
353 |
+
"rstrip": false,
|
354 |
+
"normalized": false,
|
355 |
+
"special": true
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"id": 64036,
|
359 |
+
"content": "<so>",
|
360 |
+
"single_word": false,
|
361 |
+
"lstrip": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"normalized": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"id": 64037,
|
368 |
+
"content": "<sr>",
|
369 |
+
"single_word": false,
|
370 |
+
"lstrip": false,
|
371 |
+
"rstrip": false,
|
372 |
+
"normalized": false,
|
373 |
+
"special": true
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"id": 64038,
|
377 |
+
"content": "<sv>",
|
378 |
+
"single_word": false,
|
379 |
+
"lstrip": false,
|
380 |
+
"rstrip": false,
|
381 |
+
"normalized": false,
|
382 |
+
"special": true
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"id": 64039,
|
386 |
+
"content": "<ti>",
|
387 |
+
"single_word": false,
|
388 |
+
"lstrip": false,
|
389 |
+
"rstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"special": true
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"id": 64040,
|
395 |
+
"content": "<uk>",
|
396 |
+
"single_word": false,
|
397 |
+
"lstrip": false,
|
398 |
+
"rstrip": false,
|
399 |
+
"normalized": false,
|
400 |
+
"special": true
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"id": 64041,
|
404 |
+
"content": "<ur>",
|
405 |
"single_word": false,
|
406 |
"lstrip": false,
|
407 |
"rstrip": false,
|
|
|
441 |
"single": [
|
442 |
{
|
443 |
"SpecialToken": {
|
444 |
+
"id": "<en>",
|
445 |
"type_id": 0
|
446 |
}
|
447 |
},
|
|
|
461 |
"pair": [
|
462 |
{
|
463 |
"SpecialToken": {
|
464 |
+
"id": "<en>",
|
465 |
"type_id": 0
|
466 |
}
|
467 |
},
|
|
|
494 |
"</s>"
|
495 |
]
|
496 |
},
|
497 |
+
"<en>": {
|
498 |
+
"id": "<en>",
|
499 |
"ids": [
|
500 |
+
64013
|
501 |
],
|
502 |
"tokens": [
|
503 |
+
"<en>"
|
504 |
]
|
505 |
}
|
506 |
}
|
tokenizer_config.json
CHANGED
@@ -34,7 +34,7 @@
|
|
34 |
"special": true
|
35 |
},
|
36 |
"64001": {
|
37 |
-
"content": "<
|
38 |
"lstrip": false,
|
39 |
"normalized": false,
|
40 |
"rstrip": false,
|
@@ -42,7 +42,319 @@
|
|
42 |
"special": true
|
43 |
},
|
44 |
"64002": {
|
45 |
-
"content": "<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
"lstrip": false,
|
47 |
"normalized": false,
|
48 |
"rstrip": false,
|
@@ -51,8 +363,47 @@
|
|
51 |
}
|
52 |
},
|
53 |
"additional_special_tokens": [
|
54 |
-
"<
|
55 |
-
"<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
],
|
57 |
"bos_token": "<s>",
|
58 |
"clean_up_tokenization_spaces": true,
|
|
|
34 |
"special": true
|
35 |
},
|
36 |
"64001": {
|
37 |
+
"content": "<af>",
|
38 |
"lstrip": false,
|
39 |
"normalized": false,
|
40 |
"rstrip": false,
|
|
|
42 |
"special": true
|
43 |
},
|
44 |
"64002": {
|
45 |
+
"content": "<am>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"64003": {
|
53 |
+
"content": "<ar>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"64004": {
|
61 |
+
"content": "<ast>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"64005": {
|
69 |
+
"content": "<be>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"64006": {
|
77 |
+
"content": "<bg>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"64007": {
|
85 |
+
"content": "<bn>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"64008": {
|
93 |
+
"content": "<bs>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"64009": {
|
101 |
+
"content": "<ca>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"64010": {
|
109 |
+
"content": "<cs>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"64011": {
|
117 |
+
"content": "<da>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"64012": {
|
125 |
+
"content": "<de>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"64013": {
|
133 |
+
"content": "<en>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"64014": {
|
141 |
+
"content": "<es>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"64015": {
|
149 |
+
"content": "<fr>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"64016": {
|
157 |
+
"content": "<gu>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"64017": {
|
165 |
+
"content": "<ha>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"64018": {
|
173 |
+
"content": "<he>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"64019": {
|
181 |
+
"content": "<hi>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"64020": {
|
189 |
+
"content": "<is>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"64021": {
|
197 |
+
"content": "<it>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"64022": {
|
205 |
+
"content": "<kab>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"64023": {
|
213 |
+
"content": "<kn>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"64024": {
|
221 |
+
"content": "<lb>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"64025": {
|
229 |
+
"content": "<mr>",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"64026": {
|
237 |
+
"content": "<mt>",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"64027": {
|
245 |
+
"content": "<ne>",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"64028": {
|
253 |
+
"content": "<nl>",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"64029": {
|
261 |
+
"content": "<no>",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"64030": {
|
269 |
+
"content": "<oc>",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
"64031": {
|
277 |
+
"content": "<pl>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": true
|
283 |
+
},
|
284 |
+
"64032": {
|
285 |
+
"content": "<pt>",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": true
|
291 |
+
},
|
292 |
+
"64033": {
|
293 |
+
"content": "<ro>",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": true
|
299 |
+
},
|
300 |
+
"64034": {
|
301 |
+
"content": "<ru>",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": true
|
307 |
+
},
|
308 |
+
"64035": {
|
309 |
+
"content": "<sd>",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": true
|
315 |
+
},
|
316 |
+
"64036": {
|
317 |
+
"content": "<so>",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
},
|
324 |
+
"64037": {
|
325 |
+
"content": "<sr>",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": true
|
331 |
+
},
|
332 |
+
"64038": {
|
333 |
+
"content": "<sv>",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": true
|
339 |
+
},
|
340 |
+
"64039": {
|
341 |
+
"content": "<ti>",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
"64040": {
|
349 |
+
"content": "<uk>",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": true
|
355 |
+
},
|
356 |
+
"64041": {
|
357 |
+
"content": "<ur>",
|
358 |
"lstrip": false,
|
359 |
"normalized": false,
|
360 |
"rstrip": false,
|
|
|
363 |
}
|
364 |
},
|
365 |
"additional_special_tokens": [
|
366 |
+
"<af>",
|
367 |
+
"<am>",
|
368 |
+
"<ar>",
|
369 |
+
"<ast>",
|
370 |
+
"<be>",
|
371 |
+
"<bg>",
|
372 |
+
"<bn>",
|
373 |
+
"<bs>",
|
374 |
+
"<ca>",
|
375 |
+
"<cs>",
|
376 |
+
"<da>",
|
377 |
+
"<de>",
|
378 |
+
"<en>",
|
379 |
+
"<es>",
|
380 |
+
"<fr>",
|
381 |
+
"<gu>",
|
382 |
+
"<ha>",
|
383 |
+
"<he>",
|
384 |
+
"<hi>",
|
385 |
+
"<is>",
|
386 |
+
"<it>",
|
387 |
+
"<kab>",
|
388 |
+
"<kn>",
|
389 |
+
"<lb>",
|
390 |
+
"<mr>",
|
391 |
+
"<mt>",
|
392 |
+
"<ne>",
|
393 |
+
"<nl>",
|
394 |
+
"<no>",
|
395 |
+
"<oc>",
|
396 |
+
"<pl>",
|
397 |
+
"<pt>",
|
398 |
+
"<ro>",
|
399 |
+
"<ru>",
|
400 |
+
"<sd>",
|
401 |
+
"<so>",
|
402 |
+
"<sr>",
|
403 |
+
"<sv>",
|
404 |
+
"<ti>",
|
405 |
+
"<uk>",
|
406 |
+
"<ur>"
|
407 |
],
|
408 |
"bos_token": "<s>",
|
409 |
"clean_up_tokenization_spaces": true,
|