Hugging Face's logo

jonathanjordan21
/
donut_fine_tuning_food_composition_id

Document Question Answering
Transformers
PyTorch
Indonesian
English
vision-encoder-decoder
Inference Endpoints
Model card Files Community
jonathanjordan21 commited on
Commit
d402989
•
1 Parent(s): 82d8880

Upload processor

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +11 -71
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +8 -1
special_tokens_map.json CHANGED
@@ -1,79 +1,19 @@
1
  {
2
  "additional_special_tokens": [
3
- {
4
- "content": "</s_obat>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<s_obat>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- {
18
- "content": "</s_takaran>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- {
25
- "content": "</s_desc>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
- {
32
- "content": "<s_desc>",
33
- "lstrip": false,
34
- "normalized": false,
35
- "rstrip": false,
36
- "single_word": false
37
- },
38
- {
39
- "content": "<s_takaran>",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": false,
43
- "single_word": false
44
- },
45
- {
46
- "content": "</s_komposisi>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false
51
- },
52
- {
53
- "content": "<s_komposisi>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false
58
- },
59
- {
60
- "content": "</s_kmpsi>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false
65
- },
66
- {
67
- "content": "<s_kmpsi>",
68
- "lstrip": false,
69
- "normalized": false,
70
- "rstrip": false,
71
- "single_word": false
72
- }
73
  ],
74
  "bos_token": "<s>",
75
  "cls_token": "<s>",
76
- "eos_token": "</s>",
77
  "mask_token": {
78
  "content": "<mask>",
79
  "lstrip": true,
 
1
  {
2
  "additional_special_tokens": [
3
+ "<s_kmpsi>",
4
+ "</s_kmpsi>",
5
+ "<s_obat>",
6
+ "</s_obat>",
7
+ "<s_takaran>",
8
+ "</s_takaran>",
9
+ "<s_komposisi>",
10
+ "</s_komposisi>",
11
+ "<s_desc>",
12
+ "</s_desc>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ],
14
  "bos_token": "<s>",
15
  "cls_token": "<s>",
16
+ "eos_token": "</s_kmpsi>",
17
  "mask_token": {
18
  "content": "<mask>",
19
  "lstrip": true,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -161,7 +161,14 @@
161
  "clean_up_tokenization_spaces": true,
162
  "cls_token": "<s>",
163
  "eos_token": "</s>",
164
- "mask_token": "<mask>",
 
 
 
 
 
 
 
165
  "model_max_length": 1000000000000000019884624838656,
166
  "pad_token": "<pad>",
167
  "processor_class": "DonutProcessor",
 
161
  "clean_up_tokenization_spaces": true,
162
  "cls_token": "<s>",
163
  "eos_token": "</s>",
164
+ "mask_token": {
165
+ "__type": "AddedToken",
166
+ "content": "<mask>",
167
+ "lstrip": true,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false
171
+ },
172
  "model_max_length": 1000000000000000019884624838656,
173
  "pad_token": "<pad>",
174
  "processor_class": "DonutProcessor",