Hugging Face's logo

JandC
/
donut-base-ner

Image-Text-to-Text
Transformers
PyTorch
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
JandC commited on
Commit
5a7fecc
•
1 Parent(s): bb6a4c7

End of training

Browse files
Files changed (9) hide show
  1. README.md +54 -0
  2. added_tokens.json +45 -0
  3. generation_config.json +8 -0
  4. preprocessor_config.json +26 -0
  5. pytorch_model.bin +1 -1
  6. sentencepiece.bpe.model +3 -0
  7. special_tokens_map.json +55 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +446 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: donut-base-ner
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-base-ner
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
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.34.0.dev0
52
+ - Pytorch 2.0.1+cu118
53
+ - Datasets 2.14.5
54
+ - Tokenizers 0.14.0
added_tokens.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_HS_code>": 57528,
3
+ "</s_delivery_number>": 57556,
4
+ "</s_description>": 57545,
5
+ "</s_discount>": 57562,
6
+ "</s_gross_weight>": 57525,
7
+ "</s_hs_code>": 57541,
8
+ "</s_item_index>": 57527,
9
+ "</s_item_number>": 57535,
10
+ "</s_item_quantity>": 57532,
11
+ "</s_item_value>": 57550,
12
+ "</s_line>": 57533,
13
+ "</s_manf_part_number>": 57554,
14
+ "</s_net_weight>": 57549,
15
+ "</s_origin_country>": 57538,
16
+ "</s_part_number>": 57530,
17
+ "</s_purchase_order>": 57526,
18
+ "</s_quantity_type>": 57561,
19
+ "</s_total_item_value>": 57531,
20
+ "</s_uom>": 57553,
21
+ "</s_vendor>": 57529,
22
+ "<s_HS_code>": 57536,
23
+ "<s_delivery_number>": 57555,
24
+ "<s_description>": 57559,
25
+ "<s_discount>": 57547,
26
+ "<s_gross_weight>": 57548,
27
+ "<s_hs_code>": 57539,
28
+ "<s_iitcdip>": 57523,
29
+ "<s_item_index>": 57564,
30
+ "<s_item_number>": 57544,
31
+ "<s_item_quantity>": 57543,
32
+ "<s_item_value>": 57540,
33
+ "<s_line>": 57537,
34
+ "<s_manf_part_number>": 57552,
35
+ "<s_net_weight>": 57542,
36
+ "<s_origin_country>": 57546,
37
+ "<s_part_number>": 57534,
38
+ "<s_purchase_order>": 57558,
39
+ "<s_quantity_type>": 57557,
40
+ "<s_synthdog>": 57524,
41
+ "<s_total_item_value>": 57560,
42
+ "<s_uom>": 57551,
43
+ "<s_vendor>": 57563,
44
+ "<sep/>": 57522
45
+ }
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": "4.34.0.dev0"
8
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "do_thumbnail": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "DonutImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "DonutProcessor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": [
23
+ 720,
24
+ 960
25
+ ]
26
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a984839df235be1102f796cabb26b15d7dfc85fb9cf38f74a53ae2e4396af3d
3
  size 809342745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a580af8304d0a135f74cec382127cccfd4ce113656574df00942132ff635ee
3
  size 809342745
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
+ "</s_gross_weight>",
6
+ "</s_purchase_order>",
7
+ "</s_item_index>",
8
+ "</s_HS_code>",
9
+ "</s_vendor>",
10
+ "</s_part_number>",
11
+ "</s_total_item_value>",
12
+ "</s_item_quantity>",
13
+ "</s_line>",
14
+ "<s_part_number>",
15
+ "</s_item_number>",
16
+ "<s_HS_code>",
17
+ "<s_line>",
18
+ "</s_origin_country>",
19
+ "<s_hs_code>",
20
+ "<s_item_value>",
21
+ "</s_hs_code>",
22
+ "<s_net_weight>",
23
+ "<s_item_quantity>",
24
+ "<s_item_number>",
25
+ "</s_description>",
26
+ "<s>",
27
+ "<s_origin_country>",
28
+ "<s_discount>",
29
+ "<s_gross_weight>",
30
+ "</s_net_weight>",
31
+ "</s_item_value>",
32
+ "<s_uom>",
33
+ "<s_manf_part_number>",
34
+ "</s_uom>",
35
+ "</s_manf_part_number>",
36
+ "<s_delivery_number>",
37
+ "</s_delivery_number>",
38
+ "<s_quantity_type>",
39
+ "<s_purchase_order>",
40
+ "<s_description>",
41
+ "</s>",
42
+ "<s_total_item_value>",
43
+ "</s_quantity_type>",
44
+ "</s_discount>",
45
+ "<s_vendor>",
46
+ "<s_item_index>"
47
+ ],
48
+ "bos_token": "<s>",
49
+ "cls_token": "<s>",
50
+ "eos_token": "</s>",
51
+ "mask_token": "<mask>",
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "unk_token": "<unk>"
55
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,446 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
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": true,
22
+ "normalized": false,
23
+ "rstrip": true,
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": true,
46
+ "normalized": true,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "57523": {
52
+ "content": "<s_iitcdip>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "57524": {
60
+ "content": "<s_synthdog>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "57525": {
68
+ "content": "</s_gross_weight>",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "57526": {
76
+ "content": "</s_purchase_order>",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "57527": {
84
+ "content": "</s_item_index>",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "57528": {
92
+ "content": "</s_HS_code>",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "57529": {
100
+ "content": "</s_vendor>",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "57530": {
108
+ "content": "</s_part_number>",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "57531": {
116
+ "content": "</s_total_item_value>",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "57532": {
124
+ "content": "</s_item_quantity>",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "57533": {
132
+ "content": "</s_line>",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "57534": {
140
+ "content": "<s_part_number>",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "57535": {
148
+ "content": "</s_item_number>",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "57536": {
156
+ "content": "<s_HS_code>",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "57537": {
164
+ "content": "<s_line>",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "57538": {
172
+ "content": "</s_origin_country>",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "57539": {
180
+ "content": "<s_hs_code>",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "57540": {
188
+ "content": "<s_item_value>",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "57541": {
196
+ "content": "</s_hs_code>",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "57542": {
204
+ "content": "<s_net_weight>",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "57543": {
212
+ "content": "<s_item_quantity>",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "57544": {
220
+ "content": "<s_item_number>",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "57545": {
228
+ "content": "</s_description>",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "57546": {
236
+ "content": "<s_origin_country>",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "57547": {
244
+ "content": "<s_discount>",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "57548": {
252
+ "content": "<s_gross_weight>",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "57549": {
260
+ "content": "</s_net_weight>",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "57550": {
268
+ "content": "</s_item_value>",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "57551": {
276
+ "content": "<s_uom>",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "57552": {
284
+ "content": "<s_manf_part_number>",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "57553": {
292
+ "content": "</s_uom>",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "57554": {
300
+ "content": "</s_manf_part_number>",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "57555": {
308
+ "content": "<s_delivery_number>",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "57556": {
316
+ "content": "</s_delivery_number>",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "57557": {
324
+ "content": "<s_quantity_type>",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "57558": {
332
+ "content": "<s_purchase_order>",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "57559": {
340
+ "content": "<s_description>",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "57560": {
348
+ "content": "<s_total_item_value>",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "57561": {
356
+ "content": "</s_quantity_type>",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "57562": {
364
+ "content": "</s_discount>",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "57563": {
372
+ "content": "<s_vendor>",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "57564": {
380
+ "content": "<s_item_index>",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": true
386
+ }
387
+ },
388
+ "additional_special_tokens": [
389
+ "<s_iitcdip>",
390
+ "<s_synthdog>",
391
+ "</s_gross_weight>",
392
+ "</s_purchase_order>",
393
+ "</s_item_index>",
394
+ "</s_HS_code>",
395
+ "</s_vendor>",
396
+ "</s_part_number>",
397
+ "</s_total_item_value>",
398
+ "</s_item_quantity>",
399
+ "</s_line>",
400
+ "<s_part_number>",
401
+ "</s_item_number>",
402
+ "<s_HS_code>",
403
+ "<s_line>",
404
+ "</s_origin_country>",
405
+ "<s_hs_code>",
406
+ "<s_item_value>",
407
+ "</s_hs_code>",
408
+ "<s_net_weight>",
409
+ "<s_item_quantity>",
410
+ "<s_item_number>",
411
+ "</s_description>",
412
+ "<s>",
413
+ "<s_origin_country>",
414
+ "<s_discount>",
415
+ "<s_gross_weight>",
416
+ "</s_net_weight>",
417
+ "</s_item_value>",
418
+ "<s_uom>",
419
+ "<s_manf_part_number>",
420
+ "</s_uom>",
421
+ "</s_manf_part_number>",
422
+ "<s_delivery_number>",
423
+ "</s_delivery_number>",
424
+ "<s_quantity_type>",
425
+ "<s_purchase_order>",
426
+ "<s_description>",
427
+ "</s>",
428
+ "<s_total_item_value>",
429
+ "</s_quantity_type>",
430
+ "</s_discount>",
431
+ "<s_vendor>",
432
+ "<s_item_index>"
433
+ ],
434
+ "bos_token": "<s>",
435
+ "clean_up_tokenization_spaces": true,
436
+ "cls_token": "<s>",
437
+ "eos_token": "</s>",
438
+ "mask_token": "<mask>",
439
+ "model_max_length": 1000000000000000019884624838656,
440
+ "pad_token": "<pad>",
441
+ "processor_class": "DonutProcessor",
442
+ "sep_token": "</s>",
443
+ "sp_model_kwargs": {},
444
+ "tokenizer_class": "XLMRobertaTokenizer",
445
+ "unk_token": "<unk>"
446
+ }