Upload tokenizer.json with huggingface_hub
Browse files- tokenizer.json +42 -42
tokenizer.json
CHANGED
|
@@ -46,7 +46,7 @@
|
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"normalized": false,
|
| 49 |
-
"special":
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 49111,
|
|
@@ -55,7 +55,7 @@
|
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
"normalized": false,
|
| 58 |
-
"special":
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 49112,
|
|
@@ -64,7 +64,7 @@
|
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
"normalized": false,
|
| 67 |
-
"special":
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 49113,
|
|
@@ -73,7 +73,7 @@
|
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
"normalized": false,
|
| 76 |
-
"special":
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 49114,
|
|
@@ -82,7 +82,7 @@
|
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
| 84 |
"normalized": false,
|
| 85 |
-
"special":
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 49115,
|
|
@@ -91,7 +91,7 @@
|
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
| 93 |
"normalized": false,
|
| 94 |
-
"special":
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 49116,
|
|
@@ -100,7 +100,7 @@
|
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
| 102 |
"normalized": false,
|
| 103 |
-
"special":
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 49117,
|
|
@@ -109,7 +109,7 @@
|
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
"normalized": false,
|
| 112 |
-
"special":
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 49118,
|
|
@@ -118,7 +118,7 @@
|
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
| 120 |
"normalized": false,
|
| 121 |
-
"special":
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 49119,
|
|
@@ -127,7 +127,7 @@
|
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
| 129 |
"normalized": false,
|
| 130 |
-
"special":
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 49120,
|
|
@@ -136,7 +136,7 @@
|
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
| 138 |
"normalized": false,
|
| 139 |
-
"special":
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 49121,
|
|
@@ -145,7 +145,7 @@
|
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
| 147 |
"normalized": false,
|
| 148 |
-
"special":
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 49122,
|
|
@@ -154,7 +154,7 @@
|
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
| 156 |
"normalized": false,
|
| 157 |
-
"special":
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 49123,
|
|
@@ -163,7 +163,7 @@
|
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
| 165 |
"normalized": false,
|
| 166 |
-
"special":
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 49124,
|
|
@@ -172,7 +172,7 @@
|
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
| 174 |
"normalized": false,
|
| 175 |
-
"special":
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 49125,
|
|
@@ -181,7 +181,7 @@
|
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
| 183 |
"normalized": false,
|
| 184 |
-
"special":
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 49126,
|
|
@@ -190,7 +190,7 @@
|
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
| 192 |
"normalized": false,
|
| 193 |
-
"special":
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 49127,
|
|
@@ -199,7 +199,7 @@
|
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
| 201 |
"normalized": false,
|
| 202 |
-
"special":
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 49128,
|
|
@@ -208,7 +208,7 @@
|
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
| 210 |
"normalized": false,
|
| 211 |
-
"special":
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 49129,
|
|
@@ -217,7 +217,7 @@
|
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
| 219 |
"normalized": false,
|
| 220 |
-
"special":
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 49130,
|
|
@@ -226,7 +226,7 @@
|
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
| 228 |
"normalized": false,
|
| 229 |
-
"special":
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 49131,
|
|
@@ -235,7 +235,7 @@
|
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
| 237 |
"normalized": false,
|
| 238 |
-
"special":
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 49132,
|
|
@@ -244,7 +244,7 @@
|
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
| 246 |
"normalized": false,
|
| 247 |
-
"special":
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 49133,
|
|
@@ -253,7 +253,7 @@
|
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
| 255 |
"normalized": false,
|
| 256 |
-
"special":
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 49134,
|
|
@@ -262,7 +262,7 @@
|
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
| 264 |
"normalized": false,
|
| 265 |
-
"special":
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 49135,
|
|
@@ -271,7 +271,7 @@
|
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
| 273 |
"normalized": false,
|
| 274 |
-
"special":
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 49136,
|
|
@@ -280,7 +280,7 @@
|
|
| 280 |
"lstrip": false,
|
| 281 |
"rstrip": false,
|
| 282 |
"normalized": false,
|
| 283 |
-
"special":
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 49137,
|
|
@@ -289,7 +289,7 @@
|
|
| 289 |
"lstrip": false,
|
| 290 |
"rstrip": false,
|
| 291 |
"normalized": false,
|
| 292 |
-
"special":
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 49138,
|
|
@@ -298,7 +298,7 @@
|
|
| 298 |
"lstrip": false,
|
| 299 |
"rstrip": false,
|
| 300 |
"normalized": false,
|
| 301 |
-
"special":
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 49139,
|
|
@@ -307,7 +307,7 @@
|
|
| 307 |
"lstrip": false,
|
| 308 |
"rstrip": false,
|
| 309 |
"normalized": false,
|
| 310 |
-
"special":
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 49140,
|
|
@@ -316,7 +316,7 @@
|
|
| 316 |
"lstrip": false,
|
| 317 |
"rstrip": false,
|
| 318 |
"normalized": false,
|
| 319 |
-
"special":
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 49141,
|
|
@@ -325,7 +325,7 @@
|
|
| 325 |
"lstrip": false,
|
| 326 |
"rstrip": false,
|
| 327 |
"normalized": false,
|
| 328 |
-
"special":
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 49142,
|
|
@@ -334,7 +334,7 @@
|
|
| 334 |
"lstrip": false,
|
| 335 |
"rstrip": false,
|
| 336 |
"normalized": false,
|
| 337 |
-
"special":
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 49143,
|
|
@@ -343,7 +343,7 @@
|
|
| 343 |
"lstrip": false,
|
| 344 |
"rstrip": false,
|
| 345 |
"normalized": false,
|
| 346 |
-
"special":
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 49144,
|
|
@@ -352,7 +352,7 @@
|
|
| 352 |
"lstrip": false,
|
| 353 |
"rstrip": false,
|
| 354 |
"normalized": false,
|
| 355 |
-
"special":
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 49145,
|
|
@@ -361,7 +361,7 @@
|
|
| 361 |
"lstrip": false,
|
| 362 |
"rstrip": false,
|
| 363 |
"normalized": false,
|
| 364 |
-
"special":
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 49146,
|
|
@@ -370,7 +370,7 @@
|
|
| 370 |
"lstrip": false,
|
| 371 |
"rstrip": false,
|
| 372 |
"normalized": false,
|
| 373 |
-
"special":
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 49147,
|
|
@@ -379,7 +379,7 @@
|
|
| 379 |
"lstrip": false,
|
| 380 |
"rstrip": false,
|
| 381 |
"normalized": false,
|
| 382 |
-
"special":
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 49148,
|
|
@@ -388,7 +388,7 @@
|
|
| 388 |
"lstrip": false,
|
| 389 |
"rstrip": false,
|
| 390 |
"normalized": false,
|
| 391 |
-
"special":
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 49149,
|
|
@@ -397,7 +397,7 @@
|
|
| 397 |
"lstrip": false,
|
| 398 |
"rstrip": false,
|
| 399 |
"normalized": false,
|
| 400 |
-
"special":
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 49150,
|
|
@@ -406,7 +406,7 @@
|
|
| 406 |
"lstrip": false,
|
| 407 |
"rstrip": false,
|
| 408 |
"normalized": false,
|
| 409 |
-
"special":
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 49151,
|
|
@@ -415,7 +415,7 @@
|
|
| 415 |
"lstrip": false,
|
| 416 |
"rstrip": false,
|
| 417 |
"normalized": false,
|
| 418 |
-
"special":
|
| 419 |
}
|
| 420 |
],
|
| 421 |
"normalizer": null,
|
|
|
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"normalized": false,
|
| 49 |
+
"special": false
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 49111,
|
|
|
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
"normalized": false,
|
| 58 |
+
"special": false
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 49112,
|
|
|
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
"normalized": false,
|
| 67 |
+
"special": false
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 49113,
|
|
|
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
| 75 |
"normalized": false,
|
| 76 |
+
"special": false
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 49114,
|
|
|
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
| 84 |
"normalized": false,
|
| 85 |
+
"special": false
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 49115,
|
|
|
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
| 93 |
"normalized": false,
|
| 94 |
+
"special": false
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 49116,
|
|
|
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
| 102 |
"normalized": false,
|
| 103 |
+
"special": false
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 49117,
|
|
|
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
| 111 |
"normalized": false,
|
| 112 |
+
"special": false
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 49118,
|
|
|
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
| 120 |
"normalized": false,
|
| 121 |
+
"special": false
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 49119,
|
|
|
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
| 129 |
"normalized": false,
|
| 130 |
+
"special": false
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 49120,
|
|
|
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
| 138 |
"normalized": false,
|
| 139 |
+
"special": false
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 49121,
|
|
|
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
| 147 |
"normalized": false,
|
| 148 |
+
"special": false
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 49122,
|
|
|
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
| 156 |
"normalized": false,
|
| 157 |
+
"special": false
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 49123,
|
|
|
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
| 165 |
"normalized": false,
|
| 166 |
+
"special": false
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 49124,
|
|
|
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
| 174 |
"normalized": false,
|
| 175 |
+
"special": false
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 49125,
|
|
|
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
| 183 |
"normalized": false,
|
| 184 |
+
"special": false
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 49126,
|
|
|
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
| 192 |
"normalized": false,
|
| 193 |
+
"special": false
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 49127,
|
|
|
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
| 201 |
"normalized": false,
|
| 202 |
+
"special": false
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 49128,
|
|
|
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
| 210 |
"normalized": false,
|
| 211 |
+
"special": false
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 49129,
|
|
|
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
| 219 |
"normalized": false,
|
| 220 |
+
"special": false
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 49130,
|
|
|
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
| 228 |
"normalized": false,
|
| 229 |
+
"special": false
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 49131,
|
|
|
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
| 237 |
"normalized": false,
|
| 238 |
+
"special": false
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 49132,
|
|
|
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
| 246 |
"normalized": false,
|
| 247 |
+
"special": false
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 49133,
|
|
|
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
| 255 |
"normalized": false,
|
| 256 |
+
"special": false
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 49134,
|
|
|
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
| 264 |
"normalized": false,
|
| 265 |
+
"special": false
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 49135,
|
|
|
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
| 273 |
"normalized": false,
|
| 274 |
+
"special": false
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 49136,
|
|
|
|
| 280 |
"lstrip": false,
|
| 281 |
"rstrip": false,
|
| 282 |
"normalized": false,
|
| 283 |
+
"special": false
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 49137,
|
|
|
|
| 289 |
"lstrip": false,
|
| 290 |
"rstrip": false,
|
| 291 |
"normalized": false,
|
| 292 |
+
"special": false
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 49138,
|
|
|
|
| 298 |
"lstrip": false,
|
| 299 |
"rstrip": false,
|
| 300 |
"normalized": false,
|
| 301 |
+
"special": false
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"id": 49139,
|
|
|
|
| 307 |
"lstrip": false,
|
| 308 |
"rstrip": false,
|
| 309 |
"normalized": false,
|
| 310 |
+
"special": false
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"id": 49140,
|
|
|
|
| 316 |
"lstrip": false,
|
| 317 |
"rstrip": false,
|
| 318 |
"normalized": false,
|
| 319 |
+
"special": false
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"id": 49141,
|
|
|
|
| 325 |
"lstrip": false,
|
| 326 |
"rstrip": false,
|
| 327 |
"normalized": false,
|
| 328 |
+
"special": false
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"id": 49142,
|
|
|
|
| 334 |
"lstrip": false,
|
| 335 |
"rstrip": false,
|
| 336 |
"normalized": false,
|
| 337 |
+
"special": false
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"id": 49143,
|
|
|
|
| 343 |
"lstrip": false,
|
| 344 |
"rstrip": false,
|
| 345 |
"normalized": false,
|
| 346 |
+
"special": false
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"id": 49144,
|
|
|
|
| 352 |
"lstrip": false,
|
| 353 |
"rstrip": false,
|
| 354 |
"normalized": false,
|
| 355 |
+
"special": false
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"id": 49145,
|
|
|
|
| 361 |
"lstrip": false,
|
| 362 |
"rstrip": false,
|
| 363 |
"normalized": false,
|
| 364 |
+
"special": false
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"id": 49146,
|
|
|
|
| 370 |
"lstrip": false,
|
| 371 |
"rstrip": false,
|
| 372 |
"normalized": false,
|
| 373 |
+
"special": false
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"id": 49147,
|
|
|
|
| 379 |
"lstrip": false,
|
| 380 |
"rstrip": false,
|
| 381 |
"normalized": false,
|
| 382 |
+
"special": false
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"id": 49148,
|
|
|
|
| 388 |
"lstrip": false,
|
| 389 |
"rstrip": false,
|
| 390 |
"normalized": false,
|
| 391 |
+
"special": false
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"id": 49149,
|
|
|
|
| 397 |
"lstrip": false,
|
| 398 |
"rstrip": false,
|
| 399 |
"normalized": false,
|
| 400 |
+
"special": false
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"id": 49150,
|
|
|
|
| 406 |
"lstrip": false,
|
| 407 |
"rstrip": false,
|
| 408 |
"normalized": false,
|
| 409 |
+
"special": false
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"id": 49151,
|
|
|
|
| 415 |
"lstrip": false,
|
| 416 |
"rstrip": false,
|
| 417 |
"normalized": false,
|
| 418 |
+
"special": false
|
| 419 |
}
|
| 420 |
],
|
| 421 |
"normalizer": null,
|