Upload tokenizer
Browse files- README.md +1 -1
- special_tokens_map.json +1 -1
- tokenizer_config.json +32 -32
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
base_model: facebook/mbart-large-50
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: mBART_try_v1
|
| 8 |
results: []
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
base_model: facebook/mbart-large-50
|
| 6 |
model-index:
|
| 7 |
- name: mBART_try_v1
|
| 8 |
results: []
|
special_tokens_map.json
CHANGED
|
@@ -59,7 +59,7 @@
|
|
| 59 |
"mask_token": {
|
| 60 |
"content": "<mask>",
|
| 61 |
"lstrip": true,
|
| 62 |
-
"normalized":
|
| 63 |
"rstrip": false,
|
| 64 |
"single_word": false
|
| 65 |
},
|
|
|
|
| 59 |
"mask_token": {
|
| 60 |
"content": "<mask>",
|
| 61 |
"lstrip": true,
|
| 62 |
+
"normalized": true,
|
| 63 |
"rstrip": false,
|
| 64 |
"single_word": false
|
| 65 |
},
|
tokenizer_config.json
CHANGED
|
@@ -233,15 +233,15 @@
|
|
| 233 |
"special": true
|
| 234 |
},
|
| 235 |
"250026": {
|
| 236 |
-
"content": "
|
| 237 |
-
"lstrip":
|
| 238 |
"normalized": false,
|
| 239 |
"rstrip": false,
|
| 240 |
"single_word": false,
|
| 241 |
"special": true
|
| 242 |
},
|
| 243 |
"250027": {
|
| 244 |
-
"content": "
|
| 245 |
"lstrip": false,
|
| 246 |
"normalized": false,
|
| 247 |
"rstrip": false,
|
|
@@ -249,7 +249,7 @@
|
|
| 249 |
"special": true
|
| 250 |
},
|
| 251 |
"250028": {
|
| 252 |
-
"content": "
|
| 253 |
"lstrip": false,
|
| 254 |
"normalized": false,
|
| 255 |
"rstrip": false,
|
|
@@ -257,7 +257,7 @@
|
|
| 257 |
"special": true
|
| 258 |
},
|
| 259 |
"250029": {
|
| 260 |
-
"content": "
|
| 261 |
"lstrip": false,
|
| 262 |
"normalized": false,
|
| 263 |
"rstrip": false,
|
|
@@ -265,7 +265,7 @@
|
|
| 265 |
"special": true
|
| 266 |
},
|
| 267 |
"250030": {
|
| 268 |
-
"content": "
|
| 269 |
"lstrip": false,
|
| 270 |
"normalized": false,
|
| 271 |
"rstrip": false,
|
|
@@ -273,7 +273,7 @@
|
|
| 273 |
"special": true
|
| 274 |
},
|
| 275 |
"250031": {
|
| 276 |
-
"content": "
|
| 277 |
"lstrip": false,
|
| 278 |
"normalized": false,
|
| 279 |
"rstrip": false,
|
|
@@ -281,7 +281,7 @@
|
|
| 281 |
"special": true
|
| 282 |
},
|
| 283 |
"250032": {
|
| 284 |
-
"content": "
|
| 285 |
"lstrip": false,
|
| 286 |
"normalized": false,
|
| 287 |
"rstrip": false,
|
|
@@ -289,7 +289,7 @@
|
|
| 289 |
"special": true
|
| 290 |
},
|
| 291 |
"250033": {
|
| 292 |
-
"content": "
|
| 293 |
"lstrip": false,
|
| 294 |
"normalized": false,
|
| 295 |
"rstrip": false,
|
|
@@ -297,7 +297,7 @@
|
|
| 297 |
"special": true
|
| 298 |
},
|
| 299 |
"250034": {
|
| 300 |
-
"content": "
|
| 301 |
"lstrip": false,
|
| 302 |
"normalized": false,
|
| 303 |
"rstrip": false,
|
|
@@ -305,7 +305,7 @@
|
|
| 305 |
"special": true
|
| 306 |
},
|
| 307 |
"250035": {
|
| 308 |
-
"content": "
|
| 309 |
"lstrip": false,
|
| 310 |
"normalized": false,
|
| 311 |
"rstrip": false,
|
|
@@ -313,7 +313,7 @@
|
|
| 313 |
"special": true
|
| 314 |
},
|
| 315 |
"250036": {
|
| 316 |
-
"content": "
|
| 317 |
"lstrip": false,
|
| 318 |
"normalized": false,
|
| 319 |
"rstrip": false,
|
|
@@ -321,7 +321,7 @@
|
|
| 321 |
"special": true
|
| 322 |
},
|
| 323 |
"250037": {
|
| 324 |
-
"content": "
|
| 325 |
"lstrip": false,
|
| 326 |
"normalized": false,
|
| 327 |
"rstrip": false,
|
|
@@ -329,7 +329,7 @@
|
|
| 329 |
"special": true
|
| 330 |
},
|
| 331 |
"250038": {
|
| 332 |
-
"content": "
|
| 333 |
"lstrip": false,
|
| 334 |
"normalized": false,
|
| 335 |
"rstrip": false,
|
|
@@ -337,7 +337,7 @@
|
|
| 337 |
"special": true
|
| 338 |
},
|
| 339 |
"250039": {
|
| 340 |
-
"content": "
|
| 341 |
"lstrip": false,
|
| 342 |
"normalized": false,
|
| 343 |
"rstrip": false,
|
|
@@ -345,7 +345,7 @@
|
|
| 345 |
"special": true
|
| 346 |
},
|
| 347 |
"250040": {
|
| 348 |
-
"content": "
|
| 349 |
"lstrip": false,
|
| 350 |
"normalized": false,
|
| 351 |
"rstrip": false,
|
|
@@ -353,7 +353,7 @@
|
|
| 353 |
"special": true
|
| 354 |
},
|
| 355 |
"250041": {
|
| 356 |
-
"content": "
|
| 357 |
"lstrip": false,
|
| 358 |
"normalized": false,
|
| 359 |
"rstrip": false,
|
|
@@ -361,7 +361,7 @@
|
|
| 361 |
"special": true
|
| 362 |
},
|
| 363 |
"250042": {
|
| 364 |
-
"content": "
|
| 365 |
"lstrip": false,
|
| 366 |
"normalized": false,
|
| 367 |
"rstrip": false,
|
|
@@ -369,7 +369,7 @@
|
|
| 369 |
"special": true
|
| 370 |
},
|
| 371 |
"250043": {
|
| 372 |
-
"content": "
|
| 373 |
"lstrip": false,
|
| 374 |
"normalized": false,
|
| 375 |
"rstrip": false,
|
|
@@ -377,7 +377,7 @@
|
|
| 377 |
"special": true
|
| 378 |
},
|
| 379 |
"250044": {
|
| 380 |
-
"content": "
|
| 381 |
"lstrip": false,
|
| 382 |
"normalized": false,
|
| 383 |
"rstrip": false,
|
|
@@ -385,7 +385,7 @@
|
|
| 385 |
"special": true
|
| 386 |
},
|
| 387 |
"250045": {
|
| 388 |
-
"content": "
|
| 389 |
"lstrip": false,
|
| 390 |
"normalized": false,
|
| 391 |
"rstrip": false,
|
|
@@ -393,7 +393,7 @@
|
|
| 393 |
"special": true
|
| 394 |
},
|
| 395 |
"250046": {
|
| 396 |
-
"content": "
|
| 397 |
"lstrip": false,
|
| 398 |
"normalized": false,
|
| 399 |
"rstrip": false,
|
|
@@ -401,7 +401,7 @@
|
|
| 401 |
"special": true
|
| 402 |
},
|
| 403 |
"250047": {
|
| 404 |
-
"content": "
|
| 405 |
"lstrip": false,
|
| 406 |
"normalized": false,
|
| 407 |
"rstrip": false,
|
|
@@ -409,7 +409,7 @@
|
|
| 409 |
"special": true
|
| 410 |
},
|
| 411 |
"250048": {
|
| 412 |
-
"content": "
|
| 413 |
"lstrip": false,
|
| 414 |
"normalized": false,
|
| 415 |
"rstrip": false,
|
|
@@ -417,7 +417,7 @@
|
|
| 417 |
"special": true
|
| 418 |
},
|
| 419 |
"250049": {
|
| 420 |
-
"content": "
|
| 421 |
"lstrip": false,
|
| 422 |
"normalized": false,
|
| 423 |
"rstrip": false,
|
|
@@ -425,7 +425,7 @@
|
|
| 425 |
"special": true
|
| 426 |
},
|
| 427 |
"250050": {
|
| 428 |
-
"content": "
|
| 429 |
"lstrip": false,
|
| 430 |
"normalized": false,
|
| 431 |
"rstrip": false,
|
|
@@ -433,7 +433,7 @@
|
|
| 433 |
"special": true
|
| 434 |
},
|
| 435 |
"250051": {
|
| 436 |
-
"content": "
|
| 437 |
"lstrip": false,
|
| 438 |
"normalized": false,
|
| 439 |
"rstrip": false,
|
|
@@ -441,7 +441,7 @@
|
|
| 441 |
"special": true
|
| 442 |
},
|
| 443 |
"250052": {
|
| 444 |
-
"content": "
|
| 445 |
"lstrip": false,
|
| 446 |
"normalized": false,
|
| 447 |
"rstrip": false,
|
|
@@ -449,9 +449,9 @@
|
|
| 449 |
"special": true
|
| 450 |
},
|
| 451 |
"250053": {
|
| 452 |
-
"content": "
|
| 453 |
-
"lstrip":
|
| 454 |
-
"normalized":
|
| 455 |
"rstrip": false,
|
| 456 |
"single_word": false,
|
| 457 |
"special": true
|
|
@@ -522,6 +522,6 @@
|
|
| 522 |
"sp_model_kwargs": {},
|
| 523 |
"src_lang": "en_XX",
|
| 524 |
"tgt_lang": null,
|
| 525 |
-
"tokenizer_class": "
|
| 526 |
"unk_token": "<unk>"
|
| 527 |
}
|
|
|
|
| 233 |
"special": true
|
| 234 |
},
|
| 235 |
"250026": {
|
| 236 |
+
"content": "af_ZA",
|
| 237 |
+
"lstrip": false,
|
| 238 |
"normalized": false,
|
| 239 |
"rstrip": false,
|
| 240 |
"single_word": false,
|
| 241 |
"special": true
|
| 242 |
},
|
| 243 |
"250027": {
|
| 244 |
+
"content": "az_AZ",
|
| 245 |
"lstrip": false,
|
| 246 |
"normalized": false,
|
| 247 |
"rstrip": false,
|
|
|
|
| 249 |
"special": true
|
| 250 |
},
|
| 251 |
"250028": {
|
| 252 |
+
"content": "bn_IN",
|
| 253 |
"lstrip": false,
|
| 254 |
"normalized": false,
|
| 255 |
"rstrip": false,
|
|
|
|
| 257 |
"special": true
|
| 258 |
},
|
| 259 |
"250029": {
|
| 260 |
+
"content": "fa_IR",
|
| 261 |
"lstrip": false,
|
| 262 |
"normalized": false,
|
| 263 |
"rstrip": false,
|
|
|
|
| 265 |
"special": true
|
| 266 |
},
|
| 267 |
"250030": {
|
| 268 |
+
"content": "he_IL",
|
| 269 |
"lstrip": false,
|
| 270 |
"normalized": false,
|
| 271 |
"rstrip": false,
|
|
|
|
| 273 |
"special": true
|
| 274 |
},
|
| 275 |
"250031": {
|
| 276 |
+
"content": "hr_HR",
|
| 277 |
"lstrip": false,
|
| 278 |
"normalized": false,
|
| 279 |
"rstrip": false,
|
|
|
|
| 281 |
"special": true
|
| 282 |
},
|
| 283 |
"250032": {
|
| 284 |
+
"content": "id_ID",
|
| 285 |
"lstrip": false,
|
| 286 |
"normalized": false,
|
| 287 |
"rstrip": false,
|
|
|
|
| 289 |
"special": true
|
| 290 |
},
|
| 291 |
"250033": {
|
| 292 |
+
"content": "ka_GE",
|
| 293 |
"lstrip": false,
|
| 294 |
"normalized": false,
|
| 295 |
"rstrip": false,
|
|
|
|
| 297 |
"special": true
|
| 298 |
},
|
| 299 |
"250034": {
|
| 300 |
+
"content": "km_KH",
|
| 301 |
"lstrip": false,
|
| 302 |
"normalized": false,
|
| 303 |
"rstrip": false,
|
|
|
|
| 305 |
"special": true
|
| 306 |
},
|
| 307 |
"250035": {
|
| 308 |
+
"content": "mk_MK",
|
| 309 |
"lstrip": false,
|
| 310 |
"normalized": false,
|
| 311 |
"rstrip": false,
|
|
|
|
| 313 |
"special": true
|
| 314 |
},
|
| 315 |
"250036": {
|
| 316 |
+
"content": "ml_IN",
|
| 317 |
"lstrip": false,
|
| 318 |
"normalized": false,
|
| 319 |
"rstrip": false,
|
|
|
|
| 321 |
"special": true
|
| 322 |
},
|
| 323 |
"250037": {
|
| 324 |
+
"content": "mn_MN",
|
| 325 |
"lstrip": false,
|
| 326 |
"normalized": false,
|
| 327 |
"rstrip": false,
|
|
|
|
| 329 |
"special": true
|
| 330 |
},
|
| 331 |
"250038": {
|
| 332 |
+
"content": "mr_IN",
|
| 333 |
"lstrip": false,
|
| 334 |
"normalized": false,
|
| 335 |
"rstrip": false,
|
|
|
|
| 337 |
"special": true
|
| 338 |
},
|
| 339 |
"250039": {
|
| 340 |
+
"content": "pl_PL",
|
| 341 |
"lstrip": false,
|
| 342 |
"normalized": false,
|
| 343 |
"rstrip": false,
|
|
|
|
| 345 |
"special": true
|
| 346 |
},
|
| 347 |
"250040": {
|
| 348 |
+
"content": "ps_AF",
|
| 349 |
"lstrip": false,
|
| 350 |
"normalized": false,
|
| 351 |
"rstrip": false,
|
|
|
|
| 353 |
"special": true
|
| 354 |
},
|
| 355 |
"250041": {
|
| 356 |
+
"content": "pt_XX",
|
| 357 |
"lstrip": false,
|
| 358 |
"normalized": false,
|
| 359 |
"rstrip": false,
|
|
|
|
| 361 |
"special": true
|
| 362 |
},
|
| 363 |
"250042": {
|
| 364 |
+
"content": "sv_SE",
|
| 365 |
"lstrip": false,
|
| 366 |
"normalized": false,
|
| 367 |
"rstrip": false,
|
|
|
|
| 369 |
"special": true
|
| 370 |
},
|
| 371 |
"250043": {
|
| 372 |
+
"content": "sw_KE",
|
| 373 |
"lstrip": false,
|
| 374 |
"normalized": false,
|
| 375 |
"rstrip": false,
|
|
|
|
| 377 |
"special": true
|
| 378 |
},
|
| 379 |
"250044": {
|
| 380 |
+
"content": "ta_IN",
|
| 381 |
"lstrip": false,
|
| 382 |
"normalized": false,
|
| 383 |
"rstrip": false,
|
|
|
|
| 385 |
"special": true
|
| 386 |
},
|
| 387 |
"250045": {
|
| 388 |
+
"content": "te_IN",
|
| 389 |
"lstrip": false,
|
| 390 |
"normalized": false,
|
| 391 |
"rstrip": false,
|
|
|
|
| 393 |
"special": true
|
| 394 |
},
|
| 395 |
"250046": {
|
| 396 |
+
"content": "th_TH",
|
| 397 |
"lstrip": false,
|
| 398 |
"normalized": false,
|
| 399 |
"rstrip": false,
|
|
|
|
| 401 |
"special": true
|
| 402 |
},
|
| 403 |
"250047": {
|
| 404 |
+
"content": "tl_XX",
|
| 405 |
"lstrip": false,
|
| 406 |
"normalized": false,
|
| 407 |
"rstrip": false,
|
|
|
|
| 409 |
"special": true
|
| 410 |
},
|
| 411 |
"250048": {
|
| 412 |
+
"content": "uk_UA",
|
| 413 |
"lstrip": false,
|
| 414 |
"normalized": false,
|
| 415 |
"rstrip": false,
|
|
|
|
| 417 |
"special": true
|
| 418 |
},
|
| 419 |
"250049": {
|
| 420 |
+
"content": "ur_PK",
|
| 421 |
"lstrip": false,
|
| 422 |
"normalized": false,
|
| 423 |
"rstrip": false,
|
|
|
|
| 425 |
"special": true
|
| 426 |
},
|
| 427 |
"250050": {
|
| 428 |
+
"content": "xh_ZA",
|
| 429 |
"lstrip": false,
|
| 430 |
"normalized": false,
|
| 431 |
"rstrip": false,
|
|
|
|
| 433 |
"special": true
|
| 434 |
},
|
| 435 |
"250051": {
|
| 436 |
+
"content": "gl_ES",
|
| 437 |
"lstrip": false,
|
| 438 |
"normalized": false,
|
| 439 |
"rstrip": false,
|
|
|
|
| 441 |
"special": true
|
| 442 |
},
|
| 443 |
"250052": {
|
| 444 |
+
"content": "sl_SI",
|
| 445 |
"lstrip": false,
|
| 446 |
"normalized": false,
|
| 447 |
"rstrip": false,
|
|
|
|
| 449 |
"special": true
|
| 450 |
},
|
| 451 |
"250053": {
|
| 452 |
+
"content": "<mask>",
|
| 453 |
+
"lstrip": true,
|
| 454 |
+
"normalized": true,
|
| 455 |
"rstrip": false,
|
| 456 |
"single_word": false,
|
| 457 |
"special": true
|
|
|
|
| 522 |
"sp_model_kwargs": {},
|
| 523 |
"src_lang": "en_XX",
|
| 524 |
"tgt_lang": null,
|
| 525 |
+
"tokenizer_class": "MBart50Tokenizer",
|
| 526 |
"unk_token": "<unk>"
|
| 527 |
}
|