Upload tokenizer
Browse files- added_tokens.json +12 -12
- tokenizer_config.json +16 -16
added_tokens.json
CHANGED
|
@@ -37,16 +37,16 @@
|
|
| 37 |
" ": 50259,
|
| 38 |
" ": 50258,
|
| 39 |
" ": 50257,
|
| 40 |
-
"<PAD>":
|
| 41 |
-
"<|end_of_turn|>":
|
| 42 |
-
"<|end|>":
|
| 43 |
-
"<|function_call|>":
|
| 44 |
-
"<|response|>":
|
| 45 |
-
"<|thoughts|>":
|
| 46 |
-
"Azma":
|
| 47 |
-
"Azma:":
|
| 48 |
-
"Observation:":
|
| 49 |
-
"Reference:":
|
| 50 |
-
"System:":
|
| 51 |
-
"User:":
|
| 52 |
}
|
|
|
|
| 37 |
" ": 50259,
|
| 38 |
" ": 50258,
|
| 39 |
" ": 50257,
|
| 40 |
+
"<PAD>": 50304,
|
| 41 |
+
"<|end_of_turn|>": 50301,
|
| 42 |
+
"<|end|>": 50306,
|
| 43 |
+
"<|function_call|>": 50296,
|
| 44 |
+
"<|response|>": 50299,
|
| 45 |
+
"<|thoughts|>": 50300,
|
| 46 |
+
"Azma": 50305,
|
| 47 |
+
"Azma:": 50295,
|
| 48 |
+
"Observation:": 50303,
|
| 49 |
+
"Reference:": 50302,
|
| 50 |
+
"System:": 50298,
|
| 51 |
+
"User:": 50297
|
| 52 |
}
|
tokenizer_config.json
CHANGED
|
@@ -316,15 +316,15 @@
|
|
| 316 |
"special": false
|
| 317 |
},
|
| 318 |
"50295": {
|
| 319 |
-
"content": "
|
| 320 |
"lstrip": false,
|
| 321 |
-
"normalized":
|
| 322 |
"rstrip": false,
|
| 323 |
"single_word": false,
|
| 324 |
-
"special":
|
| 325 |
},
|
| 326 |
"50296": {
|
| 327 |
-
"content": "
|
| 328 |
"lstrip": false,
|
| 329 |
"normalized": true,
|
| 330 |
"rstrip": false,
|
|
@@ -332,7 +332,7 @@
|
|
| 332 |
"special": false
|
| 333 |
},
|
| 334 |
"50297": {
|
| 335 |
-
"content": "
|
| 336 |
"lstrip": false,
|
| 337 |
"normalized": true,
|
| 338 |
"rstrip": false,
|
|
@@ -340,7 +340,7 @@
|
|
| 340 |
"special": false
|
| 341 |
},
|
| 342 |
"50298": {
|
| 343 |
-
"content": "
|
| 344 |
"lstrip": false,
|
| 345 |
"normalized": true,
|
| 346 |
"rstrip": false,
|
|
@@ -348,7 +348,7 @@
|
|
| 348 |
"special": false
|
| 349 |
},
|
| 350 |
"50299": {
|
| 351 |
-
"content": "<|
|
| 352 |
"lstrip": false,
|
| 353 |
"normalized": true,
|
| 354 |
"rstrip": false,
|
|
@@ -356,7 +356,7 @@
|
|
| 356 |
"special": false
|
| 357 |
},
|
| 358 |
"50300": {
|
| 359 |
-
"content": "
|
| 360 |
"lstrip": false,
|
| 361 |
"normalized": true,
|
| 362 |
"rstrip": false,
|
|
@@ -364,7 +364,7 @@
|
|
| 364 |
"special": false
|
| 365 |
},
|
| 366 |
"50301": {
|
| 367 |
-
"content": "<|
|
| 368 |
"lstrip": false,
|
| 369 |
"normalized": true,
|
| 370 |
"rstrip": false,
|
|
@@ -372,7 +372,7 @@
|
|
| 372 |
"special": false
|
| 373 |
},
|
| 374 |
"50302": {
|
| 375 |
-
"content": "
|
| 376 |
"lstrip": false,
|
| 377 |
"normalized": true,
|
| 378 |
"rstrip": false,
|
|
@@ -380,7 +380,7 @@
|
|
| 380 |
"special": false
|
| 381 |
},
|
| 382 |
"50303": {
|
| 383 |
-
"content": "
|
| 384 |
"lstrip": false,
|
| 385 |
"normalized": true,
|
| 386 |
"rstrip": false,
|
|
@@ -388,15 +388,15 @@
|
|
| 388 |
"special": false
|
| 389 |
},
|
| 390 |
"50304": {
|
| 391 |
-
"content": "
|
| 392 |
"lstrip": false,
|
| 393 |
-
"normalized":
|
| 394 |
"rstrip": false,
|
| 395 |
"single_word": false,
|
| 396 |
-
"special":
|
| 397 |
},
|
| 398 |
"50305": {
|
| 399 |
-
"content": "Azma
|
| 400 |
"lstrip": false,
|
| 401 |
"normalized": true,
|
| 402 |
"rstrip": false,
|
|
@@ -404,7 +404,7 @@
|
|
| 404 |
"special": false
|
| 405 |
},
|
| 406 |
"50306": {
|
| 407 |
-
"content": "
|
| 408 |
"lstrip": false,
|
| 409 |
"normalized": true,
|
| 410 |
"rstrip": false,
|
|
|
|
| 316 |
"special": false
|
| 317 |
},
|
| 318 |
"50295": {
|
| 319 |
+
"content": "Azma:",
|
| 320 |
"lstrip": false,
|
| 321 |
+
"normalized": true,
|
| 322 |
"rstrip": false,
|
| 323 |
"single_word": false,
|
| 324 |
+
"special": false
|
| 325 |
},
|
| 326 |
"50296": {
|
| 327 |
+
"content": "<|function_call|>",
|
| 328 |
"lstrip": false,
|
| 329 |
"normalized": true,
|
| 330 |
"rstrip": false,
|
|
|
|
| 332 |
"special": false
|
| 333 |
},
|
| 334 |
"50297": {
|
| 335 |
+
"content": "User:",
|
| 336 |
"lstrip": false,
|
| 337 |
"normalized": true,
|
| 338 |
"rstrip": false,
|
|
|
|
| 340 |
"special": false
|
| 341 |
},
|
| 342 |
"50298": {
|
| 343 |
+
"content": "System:",
|
| 344 |
"lstrip": false,
|
| 345 |
"normalized": true,
|
| 346 |
"rstrip": false,
|
|
|
|
| 348 |
"special": false
|
| 349 |
},
|
| 350 |
"50299": {
|
| 351 |
+
"content": "<|response|>",
|
| 352 |
"lstrip": false,
|
| 353 |
"normalized": true,
|
| 354 |
"rstrip": false,
|
|
|
|
| 356 |
"special": false
|
| 357 |
},
|
| 358 |
"50300": {
|
| 359 |
+
"content": "<|thoughts|>",
|
| 360 |
"lstrip": false,
|
| 361 |
"normalized": true,
|
| 362 |
"rstrip": false,
|
|
|
|
| 364 |
"special": false
|
| 365 |
},
|
| 366 |
"50301": {
|
| 367 |
+
"content": "<|end_of_turn|>",
|
| 368 |
"lstrip": false,
|
| 369 |
"normalized": true,
|
| 370 |
"rstrip": false,
|
|
|
|
| 372 |
"special": false
|
| 373 |
},
|
| 374 |
"50302": {
|
| 375 |
+
"content": "Reference:",
|
| 376 |
"lstrip": false,
|
| 377 |
"normalized": true,
|
| 378 |
"rstrip": false,
|
|
|
|
| 380 |
"special": false
|
| 381 |
},
|
| 382 |
"50303": {
|
| 383 |
+
"content": "Observation:",
|
| 384 |
"lstrip": false,
|
| 385 |
"normalized": true,
|
| 386 |
"rstrip": false,
|
|
|
|
| 388 |
"special": false
|
| 389 |
},
|
| 390 |
"50304": {
|
| 391 |
+
"content": "<PAD>",
|
| 392 |
"lstrip": false,
|
| 393 |
+
"normalized": false,
|
| 394 |
"rstrip": false,
|
| 395 |
"single_word": false,
|
| 396 |
+
"special": true
|
| 397 |
},
|
| 398 |
"50305": {
|
| 399 |
+
"content": "Azma",
|
| 400 |
"lstrip": false,
|
| 401 |
"normalized": true,
|
| 402 |
"rstrip": false,
|
|
|
|
| 404 |
"special": false
|
| 405 |
},
|
| 406 |
"50306": {
|
| 407 |
+
"content": "<|end|>",
|
| 408 |
"lstrip": false,
|
| 409 |
"normalized": true,
|
| 410 |
"rstrip": false,
|