Hugging Face's logo

SCUT-DLVCLab
/
lilt-roberta-en-base

Feature Extraction
Transformers
PyTorch
Safetensors
lilt
vision
Inference Endpoints
Model card Files Community
1
nielsr HF staff commited on
Commit
292af50
•
1 Parent(s): 7eb6597

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +51 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +85 -0
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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
+ "cls_token_box": [
20
+ 0,
21
+ 0,
22
+ 0,
23
+ 0
24
+ ],
25
+ "eos_token": {
26
+ "__type": "AddedToken",
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "errors": "replace",
34
+ "mask_token": {
35
+ "__type": "AddedToken",
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ },
42
+ "model_max_length": 512,
43
+ "name_or_path": "microsoft/layoutlmv3-base",
44
+ "only_label_first_subword": true,
45
+ "pad_token": {
46
+ "__type": "AddedToken",
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token_box": [
54
+ 0,
55
+ 0,
56
+ 0,
57
+ 0
58
+ ],
59
+ "pad_token_label": -100,
60
+ "sep_token": {
61
+ "__type": "AddedToken",
62
+ "content": "</s>",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false
67
+ },
68
+ "sep_token_box": [
69
+ 0,
70
+ 0,
71
+ 0,
72
+ 0
73
+ ],
74
+ "special_tokens_map_file": null,
75
+ "tokenizer_class": "LayoutLMv3Tokenizer",
76
+ "trim_offsets": true,
77
+ "unk_token": {
78
+ "__type": "AddedToken",
79
+ "content": "<unk>",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false
84
+ }
85
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff