Upload tokenizer.json
Browse files- tokenizer.json +3 -207
tokenizer.json
CHANGED
@@ -119,218 +119,14 @@
|
|
119 |
"rstrip": false,
|
120 |
"normalized": false,
|
121 |
"special": true
|
122 |
-
},
|
123 |
-
{
|
124 |
-
"id": 65001,
|
125 |
-
"content": "<extra_id_0>",
|
126 |
-
"single_word": false,
|
127 |
-
"lstrip": false,
|
128 |
-
"rstrip": false,
|
129 |
-
"normalized": false,
|
130 |
-
"special": true
|
131 |
-
},
|
132 |
-
{
|
133 |
-
"id": 65002,
|
134 |
-
"content": "<extra_id_1>",
|
135 |
-
"single_word": false,
|
136 |
-
"lstrip": false,
|
137 |
-
"rstrip": false,
|
138 |
-
"normalized": false,
|
139 |
-
"special": true
|
140 |
-
},
|
141 |
-
{
|
142 |
-
"id": 65003,
|
143 |
-
"content": "<extra_id_2>",
|
144 |
-
"single_word": false,
|
145 |
-
"lstrip": false,
|
146 |
-
"rstrip": false,
|
147 |
-
"normalized": false,
|
148 |
-
"special": true
|
149 |
-
},
|
150 |
-
{
|
151 |
-
"id": 65004,
|
152 |
-
"content": "<extra_id_3>",
|
153 |
-
"single_word": false,
|
154 |
-
"lstrip": false,
|
155 |
-
"rstrip": false,
|
156 |
-
"normalized": false,
|
157 |
-
"special": true
|
158 |
-
},
|
159 |
-
{
|
160 |
-
"id": 65005,
|
161 |
-
"content": "<extra_id_4>",
|
162 |
-
"single_word": false,
|
163 |
-
"lstrip": false,
|
164 |
-
"rstrip": false,
|
165 |
-
"normalized": false,
|
166 |
-
"special": true
|
167 |
-
},
|
168 |
-
{
|
169 |
-
"id": 65006,
|
170 |
-
"content": "<extra_id_5>",
|
171 |
-
"single_word": false,
|
172 |
-
"lstrip": false,
|
173 |
-
"rstrip": false,
|
174 |
-
"normalized": false,
|
175 |
-
"special": true
|
176 |
-
},
|
177 |
-
{
|
178 |
-
"id": 65007,
|
179 |
-
"content": "<extra_id_6>",
|
180 |
-
"single_word": false,
|
181 |
-
"lstrip": false,
|
182 |
-
"rstrip": false,
|
183 |
-
"normalized": false,
|
184 |
-
"special": true
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"id": 65008,
|
188 |
-
"content": "<extra_id_7>",
|
189 |
-
"single_word": false,
|
190 |
-
"lstrip": false,
|
191 |
-
"rstrip": false,
|
192 |
-
"normalized": false,
|
193 |
-
"special": true
|
194 |
-
},
|
195 |
-
{
|
196 |
-
"id": 65009,
|
197 |
-
"content": "<extra_id_8>",
|
198 |
-
"single_word": false,
|
199 |
-
"lstrip": false,
|
200 |
-
"rstrip": false,
|
201 |
-
"normalized": false,
|
202 |
-
"special": true
|
203 |
-
},
|
204 |
-
{
|
205 |
-
"id": 65010,
|
206 |
-
"content": "<extra_id_9>",
|
207 |
-
"single_word": false,
|
208 |
-
"lstrip": false,
|
209 |
-
"rstrip": false,
|
210 |
-
"normalized": false,
|
211 |
-
"special": true
|
212 |
-
},
|
213 |
-
{
|
214 |
-
"id": 65011,
|
215 |
-
"content": "<extra_id_10>",
|
216 |
-
"single_word": false,
|
217 |
-
"lstrip": false,
|
218 |
-
"rstrip": false,
|
219 |
-
"normalized": false,
|
220 |
-
"special": true
|
221 |
-
},
|
222 |
-
{
|
223 |
-
"id": 65012,
|
224 |
-
"content": "<extra_id_11>",
|
225 |
-
"single_word": false,
|
226 |
-
"lstrip": false,
|
227 |
-
"rstrip": false,
|
228 |
-
"normalized": false,
|
229 |
-
"special": true
|
230 |
-
},
|
231 |
-
{
|
232 |
-
"id": 65013,
|
233 |
-
"content": "<extra_id_12>",
|
234 |
-
"single_word": false,
|
235 |
-
"lstrip": false,
|
236 |
-
"rstrip": false,
|
237 |
-
"normalized": false,
|
238 |
-
"special": true
|
239 |
-
},
|
240 |
-
{
|
241 |
-
"id": 65014,
|
242 |
-
"content": "<extra_id_13>",
|
243 |
-
"single_word": false,
|
244 |
-
"lstrip": false,
|
245 |
-
"rstrip": false,
|
246 |
-
"normalized": false,
|
247 |
-
"special": true
|
248 |
-
},
|
249 |
-
{
|
250 |
-
"id": 65015,
|
251 |
-
"content": "<extra_id_14>",
|
252 |
-
"single_word": false,
|
253 |
-
"lstrip": false,
|
254 |
-
"rstrip": false,
|
255 |
-
"normalized": false,
|
256 |
-
"special": true
|
257 |
-
},
|
258 |
-
{
|
259 |
-
"id": 65016,
|
260 |
-
"content": "<extra_id_15>",
|
261 |
-
"single_word": false,
|
262 |
-
"lstrip": false,
|
263 |
-
"rstrip": false,
|
264 |
-
"normalized": false,
|
265 |
-
"special": true
|
266 |
-
},
|
267 |
-
{
|
268 |
-
"id": 65017,
|
269 |
-
"content": "<extra_id_16>",
|
270 |
-
"single_word": false,
|
271 |
-
"lstrip": false,
|
272 |
-
"rstrip": false,
|
273 |
-
"normalized": false,
|
274 |
-
"special": true
|
275 |
-
},
|
276 |
-
{
|
277 |
-
"id": 65018,
|
278 |
-
"content": "<extra_id_17>",
|
279 |
-
"single_word": false,
|
280 |
-
"lstrip": false,
|
281 |
-
"rstrip": false,
|
282 |
-
"normalized": false,
|
283 |
-
"special": true
|
284 |
-
},
|
285 |
-
{
|
286 |
-
"id": 65019,
|
287 |
-
"content": "<extra_id_18>",
|
288 |
-
"single_word": false,
|
289 |
-
"lstrip": false,
|
290 |
-
"rstrip": false,
|
291 |
-
"normalized": false,
|
292 |
-
"special": true
|
293 |
-
},
|
294 |
-
{
|
295 |
-
"id": 65020,
|
296 |
-
"content": "<extra_id_19>",
|
297 |
-
"single_word": false,
|
298 |
-
"lstrip": false,
|
299 |
-
"rstrip": false,
|
300 |
-
"normalized": false,
|
301 |
-
"special": true
|
302 |
-
},
|
303 |
-
{
|
304 |
-
"id": 65021,
|
305 |
-
"content": "<extra_id_20>",
|
306 |
-
"single_word": false,
|
307 |
-
"lstrip": false,
|
308 |
-
"rstrip": false,
|
309 |
-
"normalized": false,
|
310 |
-
"special": true
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"id": 65022,
|
314 |
-
"content": "<extra_id_21>",
|
315 |
-
"single_word": false,
|
316 |
-
"lstrip": false,
|
317 |
-
"rstrip": false,
|
318 |
-
"normalized": false,
|
319 |
-
"special": true
|
320 |
-
},
|
321 |
-
{
|
322 |
-
"id": 65023,
|
323 |
-
"content": "<extra_id_22>",
|
324 |
-
"single_word": false,
|
325 |
-
"lstrip": false,
|
326 |
-
"rstrip": false,
|
327 |
-
"normalized": false,
|
328 |
-
"special": true
|
329 |
}
|
330 |
],
|
331 |
"normalizer": {
|
332 |
"type": "Sequence",
|
333 |
"normalizers": [
|
|
|
|
|
|
|
334 |
{
|
335 |
"type": "Replace",
|
336 |
"pattern": {
|
|
|
119 |
"rstrip": false,
|
120 |
"normalized": false,
|
121 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
122 |
}
|
123 |
],
|
124 |
"normalizer": {
|
125 |
"type": "Sequence",
|
126 |
"normalizers": [
|
127 |
+
{
|
128 |
+
"type": "NFKC"
|
129 |
+
},
|
130 |
{
|
131 |
"type": "Replace",
|
132 |
"pattern": {
|