Hugging Face's logo

garden01
/
donut_sroie

Image-Text-to-Text
Transformers
PyTorch
Safetensors
vision-encoder-decoder
Model card Files
xet
 Community
1
garden01 commited on
Commit
65af6f0
·
verified ·
1 Parent(s): a31efbb

Training done

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +42 -6
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +145 -10
special_tokens_map.json CHANGED
@@ -3,9 +3,27 @@
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,
@@ -13,7 +31,25 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<pad>",
17
- "sep_token": "</s>",
18
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
 
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
  "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 CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,22 +1,157 @@
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
  }
 
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_ADDRESS>",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "57526": {
76
+ "content": "</s_ADDRESS>",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "57527": {
84
+ "content": "<s_COMPANY>",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "57528": {
92
+ "content": "</s_COMPANY>",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "57529": {
100
+ "content": "<s_DATE>",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "57530": {
108
+ "content": "</s_DATE>",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "57531": {
116
+ "content": "<s_TOTAL>",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "57532": {
124
+ "content": "</s_TOTAL>",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "57533": {
132
+ "content": "<s_sroie>",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ }
139
+ },
140
+ "additional_special_tokens": [
141
+ "<s_iitcdip>",
142
+ "<s_synthdog>"
143
+ ],
144
  "bos_token": "<s>",
145
+ "clean_up_tokenization_spaces": false,
146
  "cls_token": "<s>",
147
  "eos_token": "</s>",
148
+ "extra_special_tokens": {},
149
+ "mask_token": "<mask>",
 
 
 
 
 
 
150
  "model_max_length": 1000000000000000019884624838656,
 
151
  "pad_token": "<pad>",
152
  "processor_class": "DonutProcessor",
153
  "sep_token": "</s>",
154
  "sp_model_kwargs": {},
 
155
  "tokenizer_class": "XLMRobertaTokenizer",
156
  "unk_token": "<unk>"
157
  }