Hugging Face's logo

daekeun-ml
/
ko-trocr-base-nsmc-news-chatbot

Image-to-Text
Transformers
PyTorch
Safetensors
Korean
vision-encoder-decoder
trocr
Model card Files
xet
Community
1
daekeun-ml commited on
Commit
d999723
·
1 Parent(s): a7110bd

Upload processor

Browse files
Files changed (6) hide show
  1. merges.txt +0 -0
  2. preprocessor_config.json +18 -0
  3. special_tokens_map.json +49 -7
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +63 -15
  6. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "ViTFeatureExtractor",
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_std": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "processor_class": "TrOCRProcessor",
16
+ "resample": 2,
17
+ "size": 384
18
+ }
special_tokens_map.json CHANGED
@@ -1,9 +1,51 @@
1
  {
2
- "bos_token": "[CLS]",
3
- "cls_token": "[CLS]",
4
- "eos_token": "[SEP]",
5
- "mask_token": "[MASK]",
6
- "pad_token": "[PAD]",
7
- "sep_token": "[SEP]",
8
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,18 +1,66 @@
1
  {
2
- "bos_token": "[CLS]",
3
- "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": false,
6
- "eos_token": "[SEP]",
7
- "mask_token": "[MASK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "model_max_length": 512,
9
- "name_or_path": "daekeun-ml/ko-trocr-base-nsmc-news-chatbot",
10
- "never_split": null,
11
- "pad_token": "[PAD]",
12
- "sep_token": "[SEP]",
13
- "special_tokens_map_file": "special_tokens_map.json",
14
- "strip_accents": null,
15
- "tokenize_chinese_chars": true,
16
- "tokenizer_class": "BertTokenizer",
17
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
  "model_max_length": 512,
37
+ "name_or_path": "microsoft/trocr-base-handwritten",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "processor_class": "TrOCRProcessor",
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "special_tokens_map_file": null,
56
+ "tokenizer_class": "RobertaTokenizer",
57
+ "trim_offsets": true,
58
+ "unk_token": {
59
+ "__type": "AddedToken",
60
+ "content": "<unk>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ }
66
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff