Hugging Face's logo

currentfear
/
document_antigua

Image-to-Text
Transformers
PyTorch
Safetensors
vision-encoder-decoder
Model card Files
xet
Community
currentfear commited on
Commit
d6f8f62
·
verified ·
1 Parent(s): 0eaeeaa

Training done

Browse files
Files changed (4) hide show
  1. added_tokens.json +8 -8
  2. special_tokens_map.json +6 -42
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +10 -161
added_tokens.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "</s_firstSurname>": 57534,
3
  "</s_name>": 57532,
4
- "</s_number>": 57530,
5
- "</s_secondSurname>": 57528,
6
- "</s_type>": 57526,
7
  "<s_cord-v2>": 57535,
8
- "<s_firstSurname>": 57533,
9
  "<s_iitcdip>": 57523,
10
  "<s_name>": 57531,
11
- "<s_number>": 57529,
12
- "<s_secondSurname>": 57527,
13
  "<s_synthdog>": 57524,
14
- "<s_type>": 57525,
15
  "<sep/>": 57522
16
  }
 
1
  {
2
+ "</s_firstSurname>": 57528,
3
  "</s_name>": 57532,
4
+ "</s_number>": 57526,
5
+ "</s_secondSurname>": 57530,
6
+ "</s_type>": 57534,
7
  "<s_cord-v2>": 57535,
8
+ "<s_firstSurname>": 57527,
9
  "<s_iitcdip>": 57523,
10
  "<s_name>": 57531,
11
+ "<s_number>": 57525,
12
+ "<s_secondSurname>": 57529,
13
  "<s_synthdog>": 57524,
14
+ "<s_type>": 57533,
15
  "<sep/>": 57522
16
  }
special_tokens_map.json CHANGED
@@ -3,27 +3,9 @@
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,
@@ -31,25 +13,7 @@
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
  }
 
3
  "<s_iitcdip>",
4
  "<s_synthdog>"
5
  ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "mask_token": {
10
  "content": "<mask>",
11
  "lstrip": true,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,173 +1,22 @@
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_type>",
69
- "lstrip": false,
70
- "normalized": true,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": false
74
- },
75
- "57526": {
76
- "content": "</s_type>",
77
- "lstrip": false,
78
- "normalized": true,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": false
82
- },
83
- "57527": {
84
- "content": "<s_secondSurname>",
85
- "lstrip": false,
86
- "normalized": true,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": false
90
- },
91
- "57528": {
92
- "content": "</s_secondSurname>",
93
- "lstrip": false,
94
- "normalized": true,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": false
98
- },
99
- "57529": {
100
- "content": "<s_number>",
101
- "lstrip": false,
102
- "normalized": true,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": false
106
- },
107
- "57530": {
108
- "content": "</s_number>",
109
- "lstrip": false,
110
- "normalized": true,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": false
114
- },
115
- "57531": {
116
- "content": "<s_name>",
117
- "lstrip": false,
118
- "normalized": true,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": false
122
- },
123
- "57532": {
124
- "content": "</s_name>",
125
- "lstrip": false,
126
- "normalized": true,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": false
130
- },
131
- "57533": {
132
- "content": "<s_firstSurname>",
133
- "lstrip": false,
134
- "normalized": true,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": false
138
- },
139
- "57534": {
140
- "content": "</s_firstSurname>",
141
- "lstrip": false,
142
- "normalized": true,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": false
146
- },
147
- "57535": {
148
- "content": "<s_cord-v2>",
149
- "lstrip": false,
150
- "normalized": true,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": false
154
- }
155
- },
156
- "additional_special_tokens": [
157
- "<s_iitcdip>",
158
- "<s_synthdog>"
159
- ],
160
  "bos_token": "<s>",
161
- "clean_up_tokenization_spaces": false,
162
  "cls_token": "<s>",
163
  "eos_token": "</s>",
164
- "extra_special_tokens": {},
165
- "mask_token": "<mask>",
 
 
 
 
 
 
166
  "model_max_length": 1000000000000000019884624838656,
 
167
  "pad_token": "<pad>",
168
  "processor_class": "DonutProcessor",
169
  "sep_token": "</s>",
170
  "sp_model_kwargs": {},
 
171
  "tokenizer_class": "XLMRobertaTokenizer",
172
  "unk_token": "<unk>"
173
  }
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<s>",
 
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
  "model_max_length": 1000000000000000019884624838656,
14
+ "name_or_path": "naver-clova-ix/donut-base",
15
  "pad_token": "<pad>",
16
  "processor_class": "DonutProcessor",
17
  "sep_token": "</s>",
18
  "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
  "tokenizer_class": "XLMRobertaTokenizer",
21
  "unk_token": "<unk>"
22
  }