Hugging Face's logo

Faz1306
/
donut-base-sroie

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Faz1306 commited on
Commit
7ed0a02
·
verified ·
1 Parent(s): d1122d2

End of training

Browse files
Files changed (4) hide show
  1. preprocessor_config.json +4 -4
  2. special_tokens_map.json +10 -70
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +8 -1
preprocessor_config.json CHANGED
@@ -19,8 +19,8 @@
19
  "processor_class": "DonutProcessor",
20
  "resample": 2,
21
  "rescale_factor": 0.00392156862745098,
22
- "size": [
23
- 720,
24
- 960
25
- ]
26
  }
 
19
  "processor_class": "DonutProcessor",
20
  "resample": 2,
21
  "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "height": 960,
24
+ "width": 720
25
+ }
26
  }
special_tokens_map.json CHANGED
@@ -1,75 +1,15 @@
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,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false
65
- },
66
- {
67
- "content": "</s>",
68
- "lstrip": false,
69
- "normalized": false,
70
- "rstrip": false,
71
- "single_word": false
72
- }
73
  ],
74
  "bos_token": {
75
  "content": "<s>",
 
1
  {
2
  "additional_special_tokens": [
3
+ "<s_total>",
4
+ "</s_total>",
5
+ "<s_date>",
6
+ "</s_date>",
7
+ "<s_company>",
8
+ "</s_company>",
9
+ "<s_address>",
10
+ "</s_address>",
11
+ "<s>",
12
+ "</s>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ],
14
  "bos_token": {
15
  "content": "<s>",
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -142,15 +142,22 @@
142
  "</s>"
143
  ],
144
  "bos_token": "<s>",
145
- "clean_up_tokenization_spaces": false,
146
  "cls_token": "<s>",
147
  "eos_token": "</s>",
148
  "mask_token": "<mask>",
 
149
  "model_max_length": 1000000000000000019884624838656,
 
150
  "pad_token": "<pad>",
 
 
151
  "processor_class": "DonutProcessor",
152
  "sep_token": "</s>",
153
  "sp_model_kwargs": {},
 
154
  "tokenizer_class": "XLMRobertaTokenizer",
 
 
155
  "unk_token": "<unk>"
156
  }
 
142
  "</s>"
143
  ],
144
  "bos_token": "<s>",
145
+ "clean_up_tokenization_spaces": true,
146
  "cls_token": "<s>",
147
  "eos_token": "</s>",
148
  "mask_token": "<mask>",
149
+ "max_length": 512,
150
  "model_max_length": 1000000000000000019884624838656,
151
+ "pad_to_multiple_of": null,
152
  "pad_token": "<pad>",
153
+ "pad_token_type_id": 0,
154
+ "padding_side": "right",
155
  "processor_class": "DonutProcessor",
156
  "sep_token": "</s>",
157
  "sp_model_kwargs": {},
158
+ "stride": 0,
159
  "tokenizer_class": "XLMRobertaTokenizer",
160
+ "truncation_side": "right",
161
+ "truncation_strategy": "longest_first",
162
  "unk_token": "<unk>"
163
  }