Hugging Face's logo

hsarfraz
/
donut-irs-tax-docs-classifier

Transformers
Safetensors
donut-swin
donut
classification
irs
tax
document AI
Model card Files Community
2
hsarfraz commited on
Commit
374ba68
·
verified ·
1 Parent(s): d4f373a

Upload processor

Browse files
Files changed (6) hide show
  1. added_tokens.json +24 -0
  2. preprocessor_config.json +44 -0
  3. sentencepiece.bpe.model +3 -0
  4. special_tokens_map.json +74 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +255 -0
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_class>": 57523,
3
+ "<advertisement/>": 57524,
4
+ "<budget/>": 57525,
5
+ "<email/>": 57526,
6
+ "<file_folder/>": 57527,
7
+ "<form/>": 57528,
8
+ "<handwritten/>": 57529,
9
+ "<invoice/>": 57530,
10
+ "<letter/>": 57531,
11
+ "<memo/>": 57532,
12
+ "<news_article/>": 57533,
13
+ "<presentation/>": 57534,
14
+ "<questionnaire/>": 57535,
15
+ "<resume/>": 57536,
16
+ "<s_class>": 57537,
17
+ "<s_iitcdip>": 57538,
18
+ "<s_rvlcdip>": 57539,
19
+ "<s_synthdog>": 57540,
20
+ "<scientific_publication/>": 57541,
21
+ "<scientific_report/>": 57542,
22
+ "<sep/>": 57522,
23
+ "<specification/>": 57543
24
+ }
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
+ "height": 2560,
42
+ "width": 1920
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 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "</s_class>",
4
+ "<advertisement/>",
5
+ "<budget/>",
6
+ "<email/>",
7
+ "<file_folder/>",
8
+ "<form/>",
9
+ "<handwritten/>",
10
+ "<invoice/>",
11
+ "<letter/>",
12
+ "<memo/>",
13
+ "<news_article/>",
14
+ "<presentation/>",
15
+ "<questionnaire/>",
16
+ "<resume/>",
17
+ "<s_class>",
18
+ "<s_iitcdip>",
19
+ "<s_rvlcdip>",
20
+ "<s_synthdog>",
21
+ "<scientific_publication/>",
22
+ "<scientific_report/>",
23
+ "<specification/>"
24
+ ],
25
+ "bos_token": {
26
+ "content": "<s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "cls_token": {
33
+ "content": "<s>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "eos_token": {
40
+ "content": "</s>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "mask_token": {
47
+ "content": "<mask>",
48
+ "lstrip": true,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token": {
54
+ "content": "<pad>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "sep_token": {
61
+ "content": "</s>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "unk_token": {
68
+ "content": "<unk>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ }
74
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_class>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "57524": {
60
+ "content": "<advertisement/>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "57525": {
68
+ "content": "<budget/>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "57526": {
76
+ "content": "<email/>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "57527": {
84
+ "content": "<file_folder/>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "57528": {
92
+ "content": "<form/>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "57529": {
100
+ "content": "<handwritten/>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "57530": {
108
+ "content": "<invoice/>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "57531": {
116
+ "content": "<letter/>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "57532": {
124
+ "content": "<memo/>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "57533": {
132
+ "content": "<news_article/>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "57534": {
140
+ "content": "<presentation/>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "57535": {
148
+ "content": "<questionnaire/>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "57536": {
156
+ "content": "<resume/>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "57537": {
164
+ "content": "<s_class>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "57538": {
172
+ "content": "<s_iitcdip>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "57539": {
180
+ "content": "<s_rvlcdip>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "57540": {
188
+ "content": "<s_synthdog>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "57541": {
196
+ "content": "<scientific_publication/>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "57542": {
204
+ "content": "<scientific_report/>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "57543": {
212
+ "content": "<specification/>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ }
219
+ },
220
+ "additional_special_tokens": [
221
+ "</s_class>",
222
+ "<advertisement/>",
223
+ "<budget/>",
224
+ "<email/>",
225
+ "<file_folder/>",
226
+ "<form/>",
227
+ "<handwritten/>",
228
+ "<invoice/>",
229
+ "<letter/>",
230
+ "<memo/>",
231
+ "<news_article/>",
232
+ "<presentation/>",
233
+ "<questionnaire/>",
234
+ "<resume/>",
235
+ "<s_class>",
236
+ "<s_iitcdip>",
237
+ "<s_rvlcdip>",
238
+ "<s_synthdog>",
239
+ "<scientific_publication/>",
240
+ "<scientific_report/>",
241
+ "<specification/>"
242
+ ],
243
+ "bos_token": "<s>",
244
+ "clean_up_tokenization_spaces": true,
245
+ "cls_token": "<s>",
246
+ "eos_token": "</s>",
247
+ "mask_token": "<mask>",
248
+ "model_max_length": 1000000000000000019884624838656,
249
+ "pad_token": "<pad>",
250
+ "processor_class": "DonutProcessor",
251
+ "sep_token": "</s>",
252
+ "sp_model_kwargs": {},
253
+ "tokenizer_class": "XLMRobertaTokenizer",
254
+ "unk_token": "<unk>"
255
+ }