Upload tokenizer
Browse files- tokenizer.json +64 -73
- vocab.json +1 -1
tokenizer.json
CHANGED
|
@@ -23,7 +23,7 @@
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 2,
|
| 26 |
-
"content": "<|
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
|
@@ -32,7 +32,7 @@
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 3,
|
| 35 |
-
"content": "<|
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
|
@@ -41,7 +41,7 @@
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
| 44 |
-
"content": "<|
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
@@ -50,7 +50,7 @@
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 5,
|
| 53 |
-
"content": "<|
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
|
@@ -59,7 +59,7 @@
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 6,
|
| 62 |
-
"content": "<|
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
|
@@ -68,7 +68,7 @@
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 7,
|
| 71 |
-
"content": "<|
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
|
@@ -77,7 +77,7 @@
|
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 8,
|
| 80 |
-
"content": "<|
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
|
@@ -86,7 +86,7 @@
|
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 9,
|
| 89 |
-
"content": "<|
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
|
@@ -95,7 +95,7 @@
|
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 10,
|
| 98 |
-
"content": "<|
|
| 99 |
"single_word": false,
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
|
@@ -104,7 +104,7 @@
|
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 11,
|
| 107 |
-
"content": "<|
|
| 108 |
"single_word": false,
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
|
@@ -113,7 +113,7 @@
|
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 12,
|
| 116 |
-
"content": "<|
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
|
@@ -122,7 +122,7 @@
|
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 13,
|
| 125 |
-
"content": "<|
|
| 126 |
"single_word": false,
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
|
@@ -131,7 +131,7 @@
|
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 14,
|
| 134 |
-
"content": "<|
|
| 135 |
"single_word": false,
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
|
@@ -140,7 +140,7 @@
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 15,
|
| 143 |
-
"content": "<|
|
| 144 |
"single_word": false,
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
|
@@ -149,7 +149,7 @@
|
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 16,
|
| 152 |
-
"content": "<|
|
| 153 |
"single_word": false,
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
|
@@ -158,7 +158,7 @@
|
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 17,
|
| 161 |
-
"content": "<|
|
| 162 |
"single_word": false,
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
|
@@ -167,7 +167,7 @@
|
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 18,
|
| 170 |
-
"content": "<|
|
| 171 |
"single_word": false,
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
|
@@ -176,7 +176,7 @@
|
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 19,
|
| 179 |
-
"content": "<|
|
| 180 |
"single_word": false,
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
|
@@ -185,7 +185,7 @@
|
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 20,
|
| 188 |
-
"content": "<|
|
| 189 |
"single_word": false,
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
|
@@ -194,7 +194,7 @@
|
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 21,
|
| 197 |
-
"content": "<|
|
| 198 |
"single_word": false,
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
|
@@ -203,7 +203,7 @@
|
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 22,
|
| 206 |
-
"content": "<|
|
| 207 |
"single_word": false,
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
|
@@ -212,7 +212,7 @@
|
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 23,
|
| 215 |
-
"content": "<|
|
| 216 |
"single_word": false,
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
|
@@ -221,7 +221,7 @@
|
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 24,
|
| 224 |
-
"content": "<|
|
| 225 |
"single_word": false,
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
|
@@ -230,7 +230,7 @@
|
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 25,
|
| 233 |
-
"content": "<|
|
| 234 |
"single_word": false,
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
|
@@ -239,7 +239,7 @@
|
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 26,
|
| 242 |
-
"content": "<|
|
| 243 |
"single_word": false,
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
|
@@ -248,7 +248,7 @@
|
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 27,
|
| 251 |
-
"content": "<|
|
| 252 |
"single_word": false,
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
|
@@ -257,7 +257,7 @@
|
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 28,
|
| 260 |
-
"content": "<|
|
| 261 |
"single_word": false,
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
|
@@ -266,7 +266,7 @@
|
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 29,
|
| 269 |
-
"content": "<|
|
| 270 |
"single_word": false,
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
|
@@ -275,7 +275,7 @@
|
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 30,
|
| 278 |
-
"content": "<|
|
| 279 |
"single_word": false,
|
| 280 |
"lstrip": false,
|
| 281 |
"rstrip": false,
|
|
@@ -284,7 +284,7 @@
|
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 31,
|
| 287 |
-
"content": "<|
|
| 288 |
"single_word": false,
|
| 289 |
"lstrip": false,
|
| 290 |
"rstrip": false,
|
|
@@ -293,16 +293,7 @@
|
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 32,
|
| 296 |
-
"content": "<|
|
| 297 |
-
"single_word": false,
|
| 298 |
-
"lstrip": false,
|
| 299 |
-
"rstrip": false,
|
| 300 |
-
"normalized": false,
|
| 301 |
-
"special": true
|
| 302 |
-
},
|
| 303 |
-
{
|
| 304 |
-
"id": 33,
|
| 305 |
-
"content": "<|res_12|>",
|
| 306 |
"single_word": false,
|
| 307 |
"lstrip": false,
|
| 308 |
"rstrip": false,
|
|
@@ -327,39 +318,39 @@
|
|
| 327 |
"vocab": {
|
| 328 |
"<|endoftext|>": 0,
|
| 329 |
"<|psep|>": 1,
|
| 330 |
-
"<|
|
| 331 |
-
"<|
|
| 332 |
-
"<|
|
| 333 |
-
"<|
|
| 334 |
-
"<|
|
| 335 |
-
"<|
|
| 336 |
-
"<|
|
| 337 |
-
"<|
|
| 338 |
-
"<|
|
| 339 |
-
"<|
|
| 340 |
-
"<|
|
| 341 |
-
"<|
|
| 342 |
-
"<|
|
| 343 |
-
"<|
|
| 344 |
-
"<|
|
| 345 |
-
"<|
|
| 346 |
-
"<|
|
| 347 |
-
"<|
|
| 348 |
-
"<|
|
| 349 |
-
"<|
|
| 350 |
-
"<|
|
| 351 |
-
"<|
|
| 352 |
-
"<|
|
| 353 |
-
"<|
|
| 354 |
-
"<|
|
| 355 |
-
"<|
|
| 356 |
-
"<|
|
| 357 |
-
"<|
|
| 358 |
-
"<|
|
| 359 |
-
"<|
|
| 360 |
-
"<|
|
| 361 |
-
"
|
| 362 |
-
"
|
| 363 |
"0": 35,
|
| 364 |
"1": 36,
|
| 365 |
"2": 37,
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 2,
|
| 26 |
+
"content": "</|psep|>",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 3,
|
| 35 |
+
"content": "<|vsep|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
| 44 |
+
"content": "<|bsep|>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 5,
|
| 53 |
+
"content": "</|bsep|>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 6,
|
| 62 |
+
"content": "<|pad|>",
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 7,
|
| 71 |
+
"content": "<|meter_0|>",
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
|
|
|
| 77 |
},
|
| 78 |
{
|
| 79 |
"id": 8,
|
| 80 |
+
"content": "<|meter_1|>",
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
"rstrip": false,
|
|
|
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 9,
|
| 89 |
+
"content": "<|meter_2|>",
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
"rstrip": false,
|
|
|
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 10,
|
| 98 |
+
"content": "<|meter_3|>",
|
| 99 |
"single_word": false,
|
| 100 |
"lstrip": false,
|
| 101 |
"rstrip": false,
|
|
|
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"id": 11,
|
| 107 |
+
"content": "<|meter_4|>",
|
| 108 |
"single_word": false,
|
| 109 |
"lstrip": false,
|
| 110 |
"rstrip": false,
|
|
|
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"id": 12,
|
| 116 |
+
"content": "<|meter_5|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
"rstrip": false,
|
|
|
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"id": 13,
|
| 125 |
+
"content": "<|meter_6|>",
|
| 126 |
"single_word": false,
|
| 127 |
"lstrip": false,
|
| 128 |
"rstrip": false,
|
|
|
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"id": 14,
|
| 134 |
+
"content": "<|meter_7|>",
|
| 135 |
"single_word": false,
|
| 136 |
"lstrip": false,
|
| 137 |
"rstrip": false,
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"id": 15,
|
| 143 |
+
"content": "<|meter_8|>",
|
| 144 |
"single_word": false,
|
| 145 |
"lstrip": false,
|
| 146 |
"rstrip": false,
|
|
|
|
| 149 |
},
|
| 150 |
{
|
| 151 |
"id": 16,
|
| 152 |
+
"content": "<|meter_9|>",
|
| 153 |
"single_word": false,
|
| 154 |
"lstrip": false,
|
| 155 |
"rstrip": false,
|
|
|
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"id": 17,
|
| 161 |
+
"content": "<|meter_10|>",
|
| 162 |
"single_word": false,
|
| 163 |
"lstrip": false,
|
| 164 |
"rstrip": false,
|
|
|
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"id": 18,
|
| 170 |
+
"content": "<|meter_11|>",
|
| 171 |
"single_word": false,
|
| 172 |
"lstrip": false,
|
| 173 |
"rstrip": false,
|
|
|
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"id": 19,
|
| 179 |
+
"content": "<|meter_12|>",
|
| 180 |
"single_word": false,
|
| 181 |
"lstrip": false,
|
| 182 |
"rstrip": false,
|
|
|
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"id": 20,
|
| 188 |
+
"content": "<|meter_13|>",
|
| 189 |
"single_word": false,
|
| 190 |
"lstrip": false,
|
| 191 |
"rstrip": false,
|
|
|
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"id": 21,
|
| 197 |
+
"content": "<|meter_14|>",
|
| 198 |
"single_word": false,
|
| 199 |
"lstrip": false,
|
| 200 |
"rstrip": false,
|
|
|
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"id": 22,
|
| 206 |
+
"content": "<|meter_15|>",
|
| 207 |
"single_word": false,
|
| 208 |
"lstrip": false,
|
| 209 |
"rstrip": false,
|
|
|
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"id": 23,
|
| 215 |
+
"content": "<|res_0|>",
|
| 216 |
"single_word": false,
|
| 217 |
"lstrip": false,
|
| 218 |
"rstrip": false,
|
|
|
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"id": 24,
|
| 224 |
+
"content": "<|res_1|>",
|
| 225 |
"single_word": false,
|
| 226 |
"lstrip": false,
|
| 227 |
"rstrip": false,
|
|
|
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"id": 25,
|
| 233 |
+
"content": "<|res_2|>",
|
| 234 |
"single_word": false,
|
| 235 |
"lstrip": false,
|
| 236 |
"rstrip": false,
|
|
|
|
| 239 |
},
|
| 240 |
{
|
| 241 |
"id": 26,
|
| 242 |
+
"content": "<|res_3|>",
|
| 243 |
"single_word": false,
|
| 244 |
"lstrip": false,
|
| 245 |
"rstrip": false,
|
|
|
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"id": 27,
|
| 251 |
+
"content": "<|res_4|>",
|
| 252 |
"single_word": false,
|
| 253 |
"lstrip": false,
|
| 254 |
"rstrip": false,
|
|
|
|
| 257 |
},
|
| 258 |
{
|
| 259 |
"id": 28,
|
| 260 |
+
"content": "<|res_5|>",
|
| 261 |
"single_word": false,
|
| 262 |
"lstrip": false,
|
| 263 |
"rstrip": false,
|
|
|
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"id": 29,
|
| 269 |
+
"content": "<|res_6|>",
|
| 270 |
"single_word": false,
|
| 271 |
"lstrip": false,
|
| 272 |
"rstrip": false,
|
|
|
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"id": 30,
|
| 278 |
+
"content": "<|res_7|>",
|
| 279 |
"single_word": false,
|
| 280 |
"lstrip": false,
|
| 281 |
"rstrip": false,
|
|
|
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"id": 31,
|
| 287 |
+
"content": "<|res_8|>",
|
| 288 |
"single_word": false,
|
| 289 |
"lstrip": false,
|
| 290 |
"rstrip": false,
|
|
|
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"id": 32,
|
| 296 |
+
"content": "<|res_9|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 297 |
"single_word": false,
|
| 298 |
"lstrip": false,
|
| 299 |
"rstrip": false,
|
|
|
|
| 318 |
"vocab": {
|
| 319 |
"<|endoftext|>": 0,
|
| 320 |
"<|psep|>": 1,
|
| 321 |
+
"</|psep|>": 2,
|
| 322 |
+
"<|vsep|>": 3,
|
| 323 |
+
"<|bsep|>": 4,
|
| 324 |
+
"</|bsep|>": 5,
|
| 325 |
+
"<|pad|>": 6,
|
| 326 |
+
"<|meter_0|>": 7,
|
| 327 |
+
"<|meter_1|>": 8,
|
| 328 |
+
"<|meter_2|>": 9,
|
| 329 |
+
"<|meter_3|>": 10,
|
| 330 |
+
"<|meter_4|>": 11,
|
| 331 |
+
"<|meter_5|>": 12,
|
| 332 |
+
"<|meter_6|>": 13,
|
| 333 |
+
"<|meter_7|>": 14,
|
| 334 |
+
"<|meter_8|>": 15,
|
| 335 |
+
"<|meter_9|>": 16,
|
| 336 |
+
"<|meter_10|>": 17,
|
| 337 |
+
"<|meter_11|>": 18,
|
| 338 |
+
"<|meter_12|>": 19,
|
| 339 |
+
"<|meter_13|>": 20,
|
| 340 |
+
"<|meter_14|>": 21,
|
| 341 |
+
"<|meter_15|>": 22,
|
| 342 |
+
"<|res_0|>": 23,
|
| 343 |
+
"<|res_1|>": 24,
|
| 344 |
+
"<|res_2|>": 25,
|
| 345 |
+
"<|res_3|>": 26,
|
| 346 |
+
"<|res_4|>": 27,
|
| 347 |
+
"<|res_5|>": 28,
|
| 348 |
+
"<|res_6|>": 29,
|
| 349 |
+
"<|res_7|>": 30,
|
| 350 |
+
"<|res_8|>": 31,
|
| 351 |
+
"<|res_9|>": 32,
|
| 352 |
+
" ": 33,
|
| 353 |
+
"/": 34,
|
| 354 |
"0": 35,
|
| 355 |
"1": 36,
|
| 356 |
"2": 37,
|
vocab.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"<|endoftext|>":0,"<|psep|>":1,"<|
|
|
|
|
| 1 |
+
{"<|endoftext|>":0,"<|psep|>":1,"</|psep|>":2,"<|vsep|>":3,"<|bsep|>":4,"</|bsep|>":5,"<|pad|>":6,"<|meter_0|>":7,"<|meter_1|>":8,"<|meter_2|>":9,"<|meter_3|>":10,"<|meter_4|>":11,"<|meter_5|>":12,"<|meter_6|>":13,"<|meter_7|>":14,"<|meter_8|>":15,"<|meter_9|>":16,"<|meter_10|>":17,"<|meter_11|>":18,"<|meter_12|>":19,"<|meter_13|>":20,"<|meter_14|>":21,"<|meter_15|>":22,"<|res_0|>":23,"<|res_1|>":24,"<|res_2|>":25,"<|res_3|>":26,"<|res_4|>":27,"<|res_5|>":28,"<|res_6|>":29,"<|res_7|>":30,"<|res_8|>":31,"<|res_9|>":32," ":33,"/":34,"0":35,"1":36,"2":37,"3":38,"4":39,"5":40,"6":41,"7":42,"8":43,"9":44,"<":45,">":46,"_":47,"b":48,"e":49,"m":50,"p":51,"r":52,"s":53,"t":54,"v":55,"|":56,"~":57,"ء":58,"أ":59,"ؤ":60,"ئ":61,"ا":62,"ب":63,"ة":64,"ت":65,"ث":66,"ج":67,"ح":68,"خ":69,"د":70,"ذ":71,"ر":72,"ز":73,"س":74,"ش":75,"ص":76,"ض":77,"ط":78,"ظ":79,"ع":80,"غ":81,"ف":82,"ق":83,"ك":84,"ل":85,"م":86,"ن":87,"ه":88,"و":89,"ى":90,"ي":91,"ً":92,"ٌ":93,"ٍ":94,"َ":95,"ُ":96,"ِ":97,"ّ":98,"ْ":99}
|