Commit ·
d9fb080
1
Parent(s): 493cf67
End of training
Browse files- README.md +4 -4
- added_tokens.json +22 -0
- generation_config.json +1 -1
- pytorch_model.bin +1 -1
- special_tokens_map.json +22 -0
- tokenizer.json +198 -0
README.md
CHANGED
|
@@ -6,14 +6,14 @@ tags:
|
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
| 8 |
model-index:
|
| 9 |
-
- name: donut-
|
| 10 |
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
-
# donut-
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
|
| 19 |
|
|
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
|
|
| 48 |
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
-
- Transformers 4.
|
| 52 |
- Pytorch 2.0.1+cu118
|
| 53 |
-
- Datasets 2.14.
|
| 54 |
- Tokenizers 0.13.3
|
|
|
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
| 8 |
model-index:
|
| 9 |
+
- name: donut-ctrt
|
| 10 |
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
+
# donut-ctrt
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
|
| 19 |
|
|
|
|
| 48 |
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
+
- Transformers 4.33.1
|
| 52 |
- Pytorch 2.0.1+cu118
|
| 53 |
+
- Datasets 2.14.5
|
| 54 |
- Tokenizers 0.13.3
|
added_tokens.json
CHANGED
|
@@ -3,15 +3,26 @@
|
|
| 3 |
"</s_계약금>": 57554,
|
| 4 |
"</s_구조・용도>": 57538,
|
| 5 |
"</s_금액>": 57546,
|
|
|
|
|
|
|
| 6 |
"</s_면적>": 57530,
|
| 7 |
"</s_보증금>": 57552,
|
|
|
|
|
|
|
| 8 |
"</s_소재지>": 57534,
|
|
|
|
|
|
|
| 9 |
"</s_임차할부분>": 57532,
|
| 10 |
"</s_입금계좌>": 57544,
|
| 11 |
"</s_잔금>": 57550,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"</s_중도금>": 57548,
|
| 13 |
"</s_지급일>": 57542,
|
| 14 |
"</s_지목>": 57528,
|
|
|
|
| 15 |
"</s_토지>": 57526,
|
| 16 |
"</s_환산보증금>": 57540,
|
| 17 |
"<s_iitcdip>": 57523,
|
|
@@ -20,15 +31,26 @@
|
|
| 20 |
"<s_계약금>": 57553,
|
| 21 |
"<s_구조・용도>": 57537,
|
| 22 |
"<s_금액>": 57545,
|
|
|
|
|
|
|
| 23 |
"<s_면적>": 57529,
|
| 24 |
"<s_보증금>": 57551,
|
|
|
|
|
|
|
| 25 |
"<s_소재지>": 57533,
|
|
|
|
|
|
|
| 26 |
"<s_임차할부분>": 57531,
|
| 27 |
"<s_입금계좌>": 57543,
|
| 28 |
"<s_잔금>": 57549,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"<s_중도금>": 57547,
|
| 30 |
"<s_지급일>": 57541,
|
| 31 |
"<s_지목>": 57527,
|
|
|
|
| 32 |
"<s_토지>": 57525,
|
| 33 |
"<s_환산보증금>": 57539,
|
| 34 |
"<sep/>": 57522
|
|
|
|
| 3 |
"</s_계약금>": 57554,
|
| 4 |
"</s_구조・용도>": 57538,
|
| 5 |
"</s_금액>": 57546,
|
| 6 |
+
"</s_납부일>": 57558,
|
| 7 |
+
"</s_대리인>": 57570,
|
| 8 |
"</s_면적>": 57530,
|
| 9 |
"</s_보증금>": 57552,
|
| 10 |
+
"</s_성명(회사명)>": 57568,
|
| 11 |
+
"</s_성명>": 57574,
|
| 12 |
"</s_소재지>": 57534,
|
| 13 |
+
"</s_임대인>": 57576,
|
| 14 |
+
"</s_임차인>": 57560,
|
| 15 |
"</s_임차할부분>": 57532,
|
| 16 |
"</s_입금계좌>": 57544,
|
| 17 |
"</s_잔금>": 57550,
|
| 18 |
+
"</s_전화>": 57566,
|
| 19 |
+
"</s_주민등록번호(법인등록번호)>": 57564,
|
| 20 |
+
"</s_주민등록번호>": 57572,
|
| 21 |
+
"</s_주소>": 57562,
|
| 22 |
"</s_중도금>": 57548,
|
| 23 |
"</s_지급일>": 57542,
|
| 24 |
"</s_지목>": 57528,
|
| 25 |
+
"</s_차임(월세)>": 57556,
|
| 26 |
"</s_토지>": 57526,
|
| 27 |
"</s_환산보증금>": 57540,
|
| 28 |
"<s_iitcdip>": 57523,
|
|
|
|
| 31 |
"<s_계약금>": 57553,
|
| 32 |
"<s_구조・용도>": 57537,
|
| 33 |
"<s_금액>": 57545,
|
| 34 |
+
"<s_납부일>": 57557,
|
| 35 |
+
"<s_대리인>": 57569,
|
| 36 |
"<s_면적>": 57529,
|
| 37 |
"<s_보증금>": 57551,
|
| 38 |
+
"<s_성명(회사명)>": 57567,
|
| 39 |
+
"<s_성명>": 57573,
|
| 40 |
"<s_소재지>": 57533,
|
| 41 |
+
"<s_임대인>": 57575,
|
| 42 |
+
"<s_임차인>": 57559,
|
| 43 |
"<s_임차할부분>": 57531,
|
| 44 |
"<s_입금계좌>": 57543,
|
| 45 |
"<s_잔금>": 57549,
|
| 46 |
+
"<s_전화>": 57565,
|
| 47 |
+
"<s_주민등록번호(법인등록번호)>": 57563,
|
| 48 |
+
"<s_주민등록번호>": 57571,
|
| 49 |
+
"<s_주소>": 57561,
|
| 50 |
"<s_중도금>": 57547,
|
| 51 |
"<s_지급일>": 57541,
|
| 52 |
"<s_지목>": 57527,
|
| 53 |
+
"<s_차임(월세)>": 57555,
|
| 54 |
"<s_토지>": 57525,
|
| 55 |
"<s_환산보증금>": 57539,
|
| 56 |
"<sep/>": 57522
|
generation_config.json
CHANGED
|
@@ -4,5 +4,5 @@
|
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"forced_eos_token_id": 2,
|
| 6 |
"pad_token_id": 1,
|
| 7 |
-
"transformers_version": "4.
|
| 8 |
}
|
|
|
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"forced_eos_token_id": 2,
|
| 6 |
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.33.1"
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 809391897
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09bdc54bfb76b9f2c0bb7a75cc3c164f73dd52144256813630dcfe173ba71010
|
| 3 |
size 809391897
|
special_tokens_map.json
CHANGED
|
@@ -30,6 +30,28 @@
|
|
| 30 |
"</s_보증금>",
|
| 31 |
"<s_계약금>",
|
| 32 |
"</s_계약금>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
"<s>",
|
| 34 |
"</s>"
|
| 35 |
],
|
|
|
|
| 30 |
"</s_보증금>",
|
| 31 |
"<s_계약금>",
|
| 32 |
"</s_계약금>",
|
| 33 |
+
"<s_차임(월세)>",
|
| 34 |
+
"</s_차임(월세)>",
|
| 35 |
+
"<s_납부일>",
|
| 36 |
+
"</s_납부일>",
|
| 37 |
+
"<s_임차인>",
|
| 38 |
+
"</s_임차인>",
|
| 39 |
+
"<s_주소>",
|
| 40 |
+
"</s_주소>",
|
| 41 |
+
"<s_주민등록번호(법인등록번호)>",
|
| 42 |
+
"</s_주민등록번호(법인등록번호)>",
|
| 43 |
+
"<s_전화>",
|
| 44 |
+
"</s_전화>",
|
| 45 |
+
"<s_성명(회사명)>",
|
| 46 |
+
"</s_성명(회사명)>",
|
| 47 |
+
"<s_대리인>",
|
| 48 |
+
"</s_대리인>",
|
| 49 |
+
"<s_주민등록번호>",
|
| 50 |
+
"</s_주민등록번호>",
|
| 51 |
+
"<s_성명>",
|
| 52 |
+
"</s_성명>",
|
| 53 |
+
"<s_임대인>",
|
| 54 |
+
"</s_임대인>",
|
| 55 |
"<s>",
|
| 56 |
"</s>"
|
| 57 |
],
|
tokenizer.json
CHANGED
|
@@ -358,6 +358,204 @@
|
|
| 358 |
"rstrip": false,
|
| 359 |
"normalized": false,
|
| 360 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 361 |
}
|
| 362 |
],
|
| 363 |
"normalizer": {
|
|
|
|
| 358 |
"rstrip": false,
|
| 359 |
"normalized": false,
|
| 360 |
"special": true
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"id": 57555,
|
| 364 |
+
"content": "<s_차임(월세)>",
|
| 365 |
+
"single_word": false,
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"id": 57556,
|
| 373 |
+
"content": "</s_차임(월세)>",
|
| 374 |
+
"single_word": false,
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"id": 57557,
|
| 382 |
+
"content": "<s_납부일>",
|
| 383 |
+
"single_word": false,
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"normalized": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"id": 57558,
|
| 391 |
+
"content": "</s_납부일>",
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"lstrip": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"normalized": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"id": 57559,
|
| 400 |
+
"content": "<s_임차인>",
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"lstrip": false,
|
| 403 |
+
"rstrip": false,
|
| 404 |
+
"normalized": false,
|
| 405 |
+
"special": true
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"id": 57560,
|
| 409 |
+
"content": "</s_임차인>",
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"lstrip": false,
|
| 412 |
+
"rstrip": false,
|
| 413 |
+
"normalized": false,
|
| 414 |
+
"special": true
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"id": 57561,
|
| 418 |
+
"content": "<s_주소>",
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"lstrip": false,
|
| 421 |
+
"rstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"special": true
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"id": 57562,
|
| 427 |
+
"content": "</s_주소>",
|
| 428 |
+
"single_word": false,
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"rstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"special": true
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"id": 57563,
|
| 436 |
+
"content": "<s_주민등록번호(법인등록번호)>",
|
| 437 |
+
"single_word": false,
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"id": 57564,
|
| 445 |
+
"content": "</s_주민등록번호(법인등록번호)>",
|
| 446 |
+
"single_word": false,
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"normalized": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"id": 57565,
|
| 454 |
+
"content": "<s_전화>",
|
| 455 |
+
"single_word": false,
|
| 456 |
+
"lstrip": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"normalized": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"id": 57566,
|
| 463 |
+
"content": "</s_전화>",
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"lstrip": false,
|
| 466 |
+
"rstrip": false,
|
| 467 |
+
"normalized": false,
|
| 468 |
+
"special": true
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"id": 57567,
|
| 472 |
+
"content": "<s_성명(회사명)>",
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"lstrip": false,
|
| 475 |
+
"rstrip": false,
|
| 476 |
+
"normalized": false,
|
| 477 |
+
"special": true
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"id": 57568,
|
| 481 |
+
"content": "</s_성명(회사명)>",
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"lstrip": false,
|
| 484 |
+
"rstrip": false,
|
| 485 |
+
"normalized": false,
|
| 486 |
+
"special": true
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"id": 57569,
|
| 490 |
+
"content": "<s_대리인>",
|
| 491 |
+
"single_word": false,
|
| 492 |
+
"lstrip": false,
|
| 493 |
+
"rstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"special": true
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"id": 57570,
|
| 499 |
+
"content": "</s_대리인>",
|
| 500 |
+
"single_word": false,
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"rstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"special": true
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"id": 57571,
|
| 508 |
+
"content": "<s_주민등록번호>",
|
| 509 |
+
"single_word": false,
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"id": 57572,
|
| 517 |
+
"content": "</s_주민등록번호>",
|
| 518 |
+
"single_word": false,
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"normalized": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"id": 57573,
|
| 526 |
+
"content": "<s_성명>",
|
| 527 |
+
"single_word": false,
|
| 528 |
+
"lstrip": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"normalized": false,
|
| 531 |
+
"special": true
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"id": 57574,
|
| 535 |
+
"content": "</s_성명>",
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"lstrip": false,
|
| 538 |
+
"rstrip": false,
|
| 539 |
+
"normalized": false,
|
| 540 |
+
"special": true
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"id": 57575,
|
| 544 |
+
"content": "<s_임대인>",
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"lstrip": false,
|
| 547 |
+
"rstrip": false,
|
| 548 |
+
"normalized": false,
|
| 549 |
+
"special": true
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"id": 57576,
|
| 553 |
+
"content": "</s_임대인>",
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"lstrip": false,
|
| 556 |
+
"rstrip": false,
|
| 557 |
+
"normalized": false,
|
| 558 |
+
"special": true
|
| 559 |
}
|
| 560 |
],
|
| 561 |
"normalizer": {
|