Hugging Face's logo

lutfinn
/
donut-base-sroie

TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Model card Files
xet
 Metrics Community
lutfinn commited on
Commit
512502d
·
verified ·
1 Parent(s): 7314ca2

End of training

Browse files
Files changed (4) hide show
  1. added_tokens.json +8 -0
  2. special_tokens_map.json +56 -0
  3. tokenizer.json +88 -2
  4. tokenizer_config.json +72 -0
added_tokens.json CHANGED
@@ -1,5 +1,13 @@
1
  {
 
 
 
 
 
 
 
2
  "<s_iitcdip>": 57523,
3
  "<s_synthdog>": 57524,
 
4
  "<sep/>": 57522
5
  }
 
1
  {
2
+ "</s_address>": 57532,
3
+ "</s_company>": 57530,
4
+ "</s_date>": 57528,
5
+ "</s_total>": 57526,
6
+ "<s_address>": 57531,
7
+ "<s_company>": 57529,
8
+ "<s_date>": 57527,
9
  "<s_iitcdip>": 57523,
10
  "<s_synthdog>": 57524,
11
+ "<s_total>": 57525,
12
  "<sep/>": 57522
13
  }
special_tokens_map.json CHANGED
@@ -1,5 +1,61 @@
1
  {
2
  "additional_special_tokens": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  {
4
  "content": "<s>",
5
  "lstrip": false,
 
1
  {
2
  "additional_special_tokens": [
3
+ {
4
+ "content": "<s_total>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s_total>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<s_date>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s_date>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<s_company>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</s_company>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<s_address>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</s_address>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
  {
60
  "content": "<s>",
61
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,7 +1,21 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
@@ -74,6 +88,78 @@
74
  "rstrip": false,
75
  "normalized": false,
76
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  }
78
  ],
79
  "normalizer": {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 512
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 1,
16
+ "pad_type_id": 0,
17
+ "pad_token": "<pad>"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
88
  "rstrip": false,
89
  "normalized": false,
90
  "special": true
91
+ },
92
+ {
93
+ "id": 57525,
94
+ "content": "<s_total>",
95
+ "single_word": false,
96
+ "lstrip": false,
97
+ "rstrip": false,
98
+ "normalized": false,
99
+ "special": true
100
+ },
101
+ {
102
+ "id": 57526,
103
+ "content": "</s_total>",
104
+ "single_word": false,
105
+ "lstrip": false,
106
+ "rstrip": false,
107
+ "normalized": false,
108
+ "special": true
109
+ },
110
+ {
111
+ "id": 57527,
112
+ "content": "<s_date>",
113
+ "single_word": false,
114
+ "lstrip": false,
115
+ "rstrip": false,
116
+ "normalized": false,
117
+ "special": true
118
+ },
119
+ {
120
+ "id": 57528,
121
+ "content": "</s_date>",
122
+ "single_word": false,
123
+ "lstrip": false,
124
+ "rstrip": false,
125
+ "normalized": false,
126
+ "special": true
127
+ },
128
+ {
129
+ "id": 57529,
130
+ "content": "<s_company>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": true
136
+ },
137
+ {
138
+ "id": 57530,
139
+ "content": "</s_company>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ {
147
+ "id": 57531,
148
+ "content": "<s_address>",
149
+ "single_word": false,
150
+ "lstrip": false,
151
+ "rstrip": false,
152
+ "normalized": false,
153
+ "special": true
154
+ },
155
+ {
156
+ "id": 57532,
157
+ "content": "</s_address>",
158
+ "single_word": false,
159
+ "lstrip": false,
160
+ "rstrip": false,
161
+ "normalized": false,
162
+ "special": true
163
  }
164
  ],
165
  "normalizer": {
tokenizer_config.json CHANGED
@@ -63,9 +63,81 @@
63
  "rstrip": false,
64
  "single_word": false,
65
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
  }
67
  },
68
  "additional_special_tokens": [
 
 
 
 
 
 
 
 
69
  "<s>",
70
  "</s>"
71
  ],
 
63
  "rstrip": false,
64
  "single_word": false,
65
  "special": true
66
+ },
67
+ "57525": {
68
+ "content": "<s_total>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "57526": {
76
+ "content": "</s_total>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "57527": {
84
+ "content": "<s_date>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "57528": {
92
+ "content": "</s_date>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "57529": {
100
+ "content": "<s_company>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "57530": {
108
+ "content": "</s_company>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "57531": {
116
+ "content": "<s_address>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "57532": {
124
+ "content": "</s_address>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
  }
131
  },
132
  "additional_special_tokens": [
133
+ "<s_total>",
134
+ "</s_total>",
135
+ "<s_date>",
136
+ "</s_date>",
137
+ "<s_company>",
138
+ "</s_company>",
139
+ "<s_address>",
140
+ "</s_address>",
141
  "<s>",
142
  "</s>"
143
  ],