Hugging Face's logo

TeeA
/
Horus-OCR

Image-to-Text
Transformers
PyTorch
Safetensors
vision-encoder-decoder
image-text-to-text
donut
vision
Inference Endpoints
Model card Files Community
TeeA commited on
Commit
5566b37
•
1 Parent(s): dc3a252

Training done

Browse files
Files changed (6) hide show
  1. added_tokens.json +42 -0
  2. preprocessor_config.json +44 -0
  3. sentencepiece.bpe.model +3 -0
  4. special_tokens_map.json +55 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +380 -0
added_tokens.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_benh_vien>": 57530,
3
+ "</s_chieu>": 57560,
4
+ "</s_dia_chi>": 57548,
5
+ "</s_doi_tuong>": 57544,
6
+ "</s_drug>": 57550,
7
+ "</s_gioi_tinh>": 57540,
8
+ "</s_khoa_dieu_tri>": 57528,
9
+ "</s_lieu_thuoc>": 57552,
10
+ "</s_ma_doi_tuong>": 57546,
11
+ "</s_ma_y_te>": 57542,
12
+ "</s_sang>": 57556,
13
+ "</s_so_luong>": 57554,
14
+ "</s_so_vao_vien>": 57532,
15
+ "</s_so_y_te>": 57526,
16
+ "</s_ten_benh_nhan>": 57536,
17
+ "</s_toa_thuoc>": 57534,
18
+ "</s_trua>": 57558,
19
+ "</s_tuoi>": 57538,
20
+ "<ocr-toa-thuoc>": 57561,
21
+ "<s_benh_vien>": 57529,
22
+ "<s_chieu>": 57559,
23
+ "<s_dia_chi>": 57547,
24
+ "<s_doi_tuong>": 57543,
25
+ "<s_drug>": 57549,
26
+ "<s_gioi_tinh>": 57539,
27
+ "<s_iitcdip>": 57523,
28
+ "<s_khoa_dieu_tri>": 57527,
29
+ "<s_lieu_thuoc>": 57551,
30
+ "<s_ma_doi_tuong>": 57545,
31
+ "<s_ma_y_te>": 57541,
32
+ "<s_sang>": 57555,
33
+ "<s_so_luong>": 57553,
34
+ "<s_so_vao_vien>": 57531,
35
+ "<s_so_y_te>": 57525,
36
+ "<s_synthdog>": 57524,
37
+ "<s_ten_benh_nhan>": 57535,
38
+ "<s_toa_thuoc>": 57533,
39
+ "<s_trua>": 57557,
40
+ "<s_tuoi>": 57537,
41
+ "<sep/>": 57522
42
+ }
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
+ 960,
42
+ 1280
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_iitcdip>",
4
+ "<s_synthdog>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "cls_token": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "mask_token": {
28
+ "content": "<mask>",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<pad>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "sep_token": {
42
+ "content": "</s>",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "unk_token": {
49
+ "content": "<unk>",
50
+ "lstrip": false,
51
+ "normalized": false,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ }
55
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,380 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_so_y_te>",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "57526": {
76
+ "content": "</s_so_y_te>",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "57527": {
84
+ "content": "<s_khoa_dieu_tri>",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "57528": {
92
+ "content": "</s_khoa_dieu_tri>",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "57529": {
100
+ "content": "<s_benh_vien>",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "57530": {
108
+ "content": "</s_benh_vien>",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "57531": {
116
+ "content": "<s_so_vao_vien>",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "57532": {
124
+ "content": "</s_so_vao_vien>",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "57533": {
132
+ "content": "<s_toa_thuoc>",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "57534": {
140
+ "content": "</s_toa_thuoc>",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "57535": {
148
+ "content": "<s_ten_benh_nhan>",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "57536": {
156
+ "content": "</s_ten_benh_nhan>",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "57537": {
164
+ "content": "<s_tuoi>",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "57538": {
172
+ "content": "</s_tuoi>",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "57539": {
180
+ "content": "<s_gioi_tinh>",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "57540": {
188
+ "content": "</s_gioi_tinh>",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "57541": {
196
+ "content": "<s_ma_y_te>",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "57542": {
204
+ "content": "</s_ma_y_te>",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "57543": {
212
+ "content": "<s_doi_tuong>",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "57544": {
220
+ "content": "</s_doi_tuong>",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "57545": {
228
+ "content": "<s_ma_doi_tuong>",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "57546": {
236
+ "content": "</s_ma_doi_tuong>",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "57547": {
244
+ "content": "<s_dia_chi>",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "57548": {
252
+ "content": "</s_dia_chi>",
253
+ "lstrip": false,
254
+ "normalized": true,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "57549": {
260
+ "content": "<s_drug>",
261
+ "lstrip": false,
262
+ "normalized": true,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "57550": {
268
+ "content": "</s_drug>",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "57551": {
276
+ "content": "<s_lieu_thuoc>",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "57552": {
284
+ "content": "</s_lieu_thuoc>",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "57553": {
292
+ "content": "<s_so_luong>",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "57554": {
300
+ "content": "</s_so_luong>",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "57555": {
308
+ "content": "<s_sang>",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "57556": {
316
+ "content": "</s_sang>",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "57557": {
324
+ "content": "<s_trua>",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "57558": {
332
+ "content": "</s_trua>",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "57559": {
340
+ "content": "<s_chieu>",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "57560": {
348
+ "content": "</s_chieu>",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "57561": {
356
+ "content": "<ocr-toa-thuoc>",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ }
363
+ },
364
+ "additional_special_tokens": [
365
+ "<s_iitcdip>",
366
+ "<s_synthdog>"
367
+ ],
368
+ "bos_token": "<s>",
369
+ "clean_up_tokenization_spaces": true,
370
+ "cls_token": "<s>",
371
+ "eos_token": "</s>",
372
+ "mask_token": "<mask>",
373
+ "model_max_length": 1000000000000000019884624838656,
374
+ "pad_token": "<pad>",
375
+ "processor_class": "DonutProcessor",
376
+ "sep_token": "</s>",
377
+ "sp_model_kwargs": {},
378
+ "tokenizer_class": "XLMRobertaTokenizer",
379
+ "unk_token": "<unk>"
380
+ }