Hugging Face's logo

emisilab
/
model-ocr-ktp-v1

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
emisilab commited on
Commit
3ec8e08
•
1 Parent(s): 792543d

End of training

Browse files
Files changed (10) hide show
  1. README.md +51 -0
  2. added_tokens.json +43 -0
  3. generation_config.json +8 -0
  4. model.safetensors +1 -1
  5. preprocessor_config.json +44 -0
  6. sentencepiece.bpe.model +3 -0
  7. special_tokens_map.json +333 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +426 -0
  10. training_args.bin +1 -1
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: naver-clova-ix/donut-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ model-index:
9
+ - name: model-ocr-ktp-v1
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
+ # model-ocr-ktp-v1
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
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 5
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Framework versions
47
+
48
+ - Transformers 4.39.0
49
+ - Pytorch 2.2.1+cu121
50
+ - Datasets 2.18.0
51
+ - Tokenizers 0.15.2
added_tokens.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_KTP_AGAMA>": 57562,
3
+ "</s_KTP_ALAMAT>": 57560,
4
+ "</s_KTP_BERLAKU_HINGGA>": 57558,
5
+ "</s_KTP_DIKELUARKAN_DI>": 57556,
6
+ "</s_KTP_DIKELUARKAN_TGL>": 57554,
7
+ "</s_KTP_GOL_DARAH>": 57552,
8
+ "</s_KTP_JENIS_KELAMIN>": 57550,
9
+ "</s_KTP_KABUPATEN_MADYA>": 57548,
10
+ "</s_KTP_KECAMATAN>": 57546,
11
+ "</s_KTP_KELURAHAN>": 57544,
12
+ "</s_KTP_KEWARGANEGARAAN>": 57542,
13
+ "</s_KTP_NAMA>": 57540,
14
+ "</s_KTP_NIK>": 57538,
15
+ "</s_KTP_PEKERJAAN>": 57536,
16
+ "</s_KTP_PROVINSI>": 57534,
17
+ "</s_KTP_RT_RW>": 57532,
18
+ "</s_KTP_STATUS_PERKAWINAN>": 57530,
19
+ "</s_KTP_TEMPAT_LAHIR>": 57528,
20
+ "</s_KTP_TGL_LAHIR>": 57526,
21
+ "<s_KTP_AGAMA>": 57561,
22
+ "<s_KTP_ALAMAT>": 57559,
23
+ "<s_KTP_BERLAKU_HINGGA>": 57557,
24
+ "<s_KTP_DIKELUARKAN_DI>": 57555,
25
+ "<s_KTP_DIKELUARKAN_TGL>": 57553,
26
+ "<s_KTP_GOL_DARAH>": 57551,
27
+ "<s_KTP_JENIS_KELAMIN>": 57549,
28
+ "<s_KTP_KABUPATEN_MADYA>": 57547,
29
+ "<s_KTP_KECAMATAN>": 57545,
30
+ "<s_KTP_KELURAHAN>": 57543,
31
+ "<s_KTP_KEWARGANEGARAAN>": 57541,
32
+ "<s_KTP_NAMA>": 57539,
33
+ "<s_KTP_NIK>": 57537,
34
+ "<s_KTP_PEKERJAAN>": 57535,
35
+ "<s_KTP_PROVINSI>": 57533,
36
+ "<s_KTP_RT_RW>": 57531,
37
+ "<s_KTP_STATUS_PERKAWINAN>": 57529,
38
+ "<s_KTP_TEMPAT_LAHIR>": 57527,
39
+ "<s_KTP_TGL_LAHIR>": 57525,
40
+ "<s_iitcdip>": 57523,
41
+ "<s_synthdog>": 57524,
42
+ "<sep/>": 57522
43
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.39.0"
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90d93266497bfcc3fa3b68aadd86c91f24467a538538d49fcf01c5a177008bc8
3
  size 809226392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e886891f87bac5cee024dbcb086581294e2b57c03258f17b1308c1cbd34f3a
3
  size 809226392
preprocessor_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_thumbnail",
8
+ "do_align_long_axis",
9
+ "do_pad",
10
+ "random_padding",
11
+ "do_rescale",
12
+ "rescale_factor",
13
+ "do_normalize",
14
+ "image_mean",
15
+ "image_std",
16
+ "return_tensors",
17
+ "data_format",
18
+ "input_data_format"
19
+ ],
20
+ "do_align_long_axis": false,
21
+ "do_normalize": true,
22
+ "do_pad": true,
23
+ "do_rescale": true,
24
+ "do_resize": true,
25
+ "do_thumbnail": true,
26
+ "image_mean": [
27
+ 0.5,
28
+ 0.5,
29
+ 0.5
30
+ ],
31
+ "image_processor_type": "DonutImageProcessor",
32
+ "image_std": [
33
+ 0.5,
34
+ 0.5,
35
+ 0.5
36
+ ],
37
+ "processor_class": "DonutProcessor",
38
+ "resample": 2,
39
+ "rescale_factor": 0.00392156862745098,
40
+ "size": [
41
+ 720,
42
+ 960
43
+ ]
44
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
3
+ size 1296245
special_tokens_map.json ADDED
@@ -0,0 +1,333 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s_KTP_TGL_LAHIR>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s_KTP_TGL_LAHIR>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<s_KTP_TEMPAT_LAHIR>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s_KTP_TEMPAT_LAHIR>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<s_KTP_STATUS_PERKAWINAN>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</s_KTP_STATUS_PERKAWINAN>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<s_KTP_RT_RW>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</s_KTP_RT_RW>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<s_KTP_PROVINSI>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</s_KTP_PROVINSI>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<s_KTP_PEKERJAAN>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "</s_KTP_PEKERJAAN>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<s_KTP_NIK>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "</s_KTP_NIK>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<s_KTP_NAMA>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "</s_KTP_NAMA>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<s_KTP_KEWARGANEGARAAN>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "</s_KTP_KEWARGANEGARAAN>",
124
+ "lstrip": false,
125
+ "normalized": false,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<s_KTP_KELURAHAN>",
131
+ "lstrip": false,
132
+ "normalized": false,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "</s_KTP_KELURAHAN>",
138
+ "lstrip": false,
139
+ "normalized": false,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<s_KTP_KECAMATAN>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "</s_KTP_KECAMATAN>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<s_KTP_KABUPATEN_MADYA>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "</s_KTP_KABUPATEN_MADYA>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<s_KTP_JENIS_KELAMIN>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "</s_KTP_JENIS_KELAMIN>",
180
+ "lstrip": false,
181
+ "normalized": false,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<s_KTP_GOL_DARAH>",
187
+ "lstrip": false,
188
+ "normalized": false,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "</s_KTP_GOL_DARAH>",
194
+ "lstrip": false,
195
+ "normalized": false,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<s_KTP_DIKELUARKAN_TGL>",
201
+ "lstrip": false,
202
+ "normalized": false,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "</s_KTP_DIKELUARKAN_TGL>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<s_KTP_DIKELUARKAN_DI>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "</s_KTP_DIKELUARKAN_DI>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<s_KTP_BERLAKU_HINGGA>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "</s_KTP_BERLAKU_HINGGA>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<s_KTP_ALAMAT>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "</s_KTP_ALAMAT>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<s_KTP_AGAMA>",
257
+ "lstrip": false,
258
+ "normalized": false,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "</s_KTP_AGAMA>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<s>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "</s>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ }
283
+ ],
284
+ "bos_token": {
285
+ "content": "<s>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false
290
+ },
291
+ "cls_token": {
292
+ "content": "<s>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false
297
+ },
298
+ "eos_token": {
299
+ "content": "</s>",
300
+ "lstrip": false,
301
+ "normalized": false,
302
+ "rstrip": false,
303
+ "single_word": false
304
+ },
305
+ "mask_token": {
306
+ "content": "<mask>",
307
+ "lstrip": true,
308
+ "normalized": true,
309
+ "rstrip": false,
310
+ "single_word": false
311
+ },
312
+ "pad_token": {
313
+ "content": "<pad>",
314
+ "lstrip": false,
315
+ "normalized": false,
316
+ "rstrip": false,
317
+ "single_word": false
318
+ },
319
+ "sep_token": {
320
+ "content": "</s>",
321
+ "lstrip": false,
322
+ "normalized": false,
323
+ "rstrip": false,
324
+ "single_word": false
325
+ },
326
+ "unk_token": {
327
+ "content": "<unk>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false
332
+ }
333
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,426 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "57521": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "57522": {
44
+ "content": "<sep/>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "57523": {
52
+ "content": "<s_iitcdip>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "57524": {
60
+ "content": "<s_synthdog>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "57525": {
68
+ "content": "<s_KTP_TGL_LAHIR>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "57526": {
76
+ "content": "</s_KTP_TGL_LAHIR>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "57527": {
84
+ "content": "<s_KTP_TEMPAT_LAHIR>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "57528": {
92
+ "content": "</s_KTP_TEMPAT_LAHIR>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "57529": {
100
+ "content": "<s_KTP_STATUS_PERKAWINAN>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "57530": {
108
+ "content": "</s_KTP_STATUS_PERKAWINAN>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "57531": {
116
+ "content": "<s_KTP_RT_RW>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "57532": {
124
+ "content": "</s_KTP_RT_RW>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "57533": {
132
+ "content": "<s_KTP_PROVINSI>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "57534": {
140
+ "content": "</s_KTP_PROVINSI>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "57535": {
148
+ "content": "<s_KTP_PEKERJAAN>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "57536": {
156
+ "content": "</s_KTP_PEKERJAAN>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "57537": {
164
+ "content": "<s_KTP_NIK>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "57538": {
172
+ "content": "</s_KTP_NIK>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "57539": {
180
+ "content": "<s_KTP_NAMA>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "57540": {
188
+ "content": "</s_KTP_NAMA>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "57541": {
196
+ "content": "<s_KTP_KEWARGANEGARAAN>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "57542": {
204
+ "content": "</s_KTP_KEWARGANEGARAAN>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "57543": {
212
+ "content": "<s_KTP_KELURAHAN>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "57544": {
220
+ "content": "</s_KTP_KELURAHAN>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "57545": {
228
+ "content": "<s_KTP_KECAMATAN>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "57546": {
236
+ "content": "</s_KTP_KECAMATAN>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "57547": {
244
+ "content": "<s_KTP_KABUPATEN_MADYA>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "57548": {
252
+ "content": "</s_KTP_KABUPATEN_MADYA>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "57549": {
260
+ "content": "<s_KTP_JENIS_KELAMIN>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "57550": {
268
+ "content": "</s_KTP_JENIS_KELAMIN>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "57551": {
276
+ "content": "<s_KTP_GOL_DARAH>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "57552": {
284
+ "content": "</s_KTP_GOL_DARAH>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "57553": {
292
+ "content": "<s_KTP_DIKELUARKAN_TGL>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "57554": {
300
+ "content": "</s_KTP_DIKELUARKAN_TGL>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "57555": {
308
+ "content": "<s_KTP_DIKELUARKAN_DI>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "57556": {
316
+ "content": "</s_KTP_DIKELUARKAN_DI>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "57557": {
324
+ "content": "<s_KTP_BERLAKU_HINGGA>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "57558": {
332
+ "content": "</s_KTP_BERLAKU_HINGGA>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "57559": {
340
+ "content": "<s_KTP_ALAMAT>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "57560": {
348
+ "content": "</s_KTP_ALAMAT>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "57561": {
356
+ "content": "<s_KTP_AGAMA>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "57562": {
364
+ "content": "</s_KTP_AGAMA>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ }
371
+ },
372
+ "additional_special_tokens": [
373
+ "<s_KTP_TGL_LAHIR>",
374
+ "</s_KTP_TGL_LAHIR>",
375
+ "<s_KTP_TEMPAT_LAHIR>",
376
+ "</s_KTP_TEMPAT_LAHIR>",
377
+ "<s_KTP_STATUS_PERKAWINAN>",
378
+ "</s_KTP_STATUS_PERKAWINAN>",
379
+ "<s_KTP_RT_RW>",
380
+ "</s_KTP_RT_RW>",
381
+ "<s_KTP_PROVINSI>",
382
+ "</s_KTP_PROVINSI>",
383
+ "<s_KTP_PEKERJAAN>",
384
+ "</s_KTP_PEKERJAAN>",
385
+ "<s_KTP_NIK>",
386
+ "</s_KTP_NIK>",
387
+ "<s_KTP_NAMA>",
388
+ "</s_KTP_NAMA>",
389
+ "<s_KTP_KEWARGANEGARAAN>",
390
+ "</s_KTP_KEWARGANEGARAAN>",
391
+ "<s_KTP_KELURAHAN>",
392
+ "</s_KTP_KELURAHAN>",
393
+ "<s_KTP_KECAMATAN>",
394
+ "</s_KTP_KECAMATAN>",
395
+ "<s_KTP_KABUPATEN_MADYA>",
396
+ "</s_KTP_KABUPATEN_MADYA>",
397
+ "<s_KTP_JENIS_KELAMIN>",
398
+ "</s_KTP_JENIS_KELAMIN>",
399
+ "<s_KTP_GOL_DARAH>",
400
+ "</s_KTP_GOL_DARAH>",
401
+ "<s_KTP_DIKELUARKAN_TGL>",
402
+ "</s_KTP_DIKELUARKAN_TGL>",
403
+ "<s_KTP_DIKELUARKAN_DI>",
404
+ "</s_KTP_DIKELUARKAN_DI>",
405
+ "<s_KTP_BERLAKU_HINGGA>",
406
+ "</s_KTP_BERLAKU_HINGGA>",
407
+ "<s_KTP_ALAMAT>",
408
+ "</s_KTP_ALAMAT>",
409
+ "<s_KTP_AGAMA>",
410
+ "</s_KTP_AGAMA>",
411
+ "<s>",
412
+ "</s>"
413
+ ],
414
+ "bos_token": "<s>",
415
+ "clean_up_tokenization_spaces": true,
416
+ "cls_token": "<s>",
417
+ "eos_token": "</s>",
418
+ "mask_token": "<mask>",
419
+ "model_max_length": 1000000000000000019884624838656,
420
+ "pad_token": "<pad>",
421
+ "processor_class": "DonutProcessor",
422
+ "sep_token": "</s>",
423
+ "sp_model_kwargs": {},
424
+ "tokenizer_class": "XLMRobertaTokenizer",
425
+ "unk_token": "<unk>"
426
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d959ff98c7105e6d2fa3ba7408b867edef3099dbee3219b39c64d0213a5f245c
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f2c757b5c5de5fd9d298d9d1023c6c204516a16d81023b02dfd8e791bd87044
3
  size 4984