nielsr HF staff commited on
Commit
64489d5
1 Parent(s): 025bcc2

Upload tokenizer

Browse files
.gitattributes CHANGED
@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
33
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "cls_token_box": [
5
+ 0,
6
+ 0,
7
+ 0,
8
+ 0
9
+ ],
10
+ "eos_token": "</s>",
11
+ "mask_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<mask>",
14
+ "lstrip": true,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "name_or_path": "microsoft/layoutxlm-base",
20
+ "only_label_first_subword": true,
21
+ "pad_token": "<pad>",
22
+ "pad_token_box": [
23
+ 0,
24
+ 0,
25
+ 0,
26
+ 0
27
+ ],
28
+ "pad_token_label": -100,
29
+ "sep_token": "</s>",
30
+ "sep_token_box": [
31
+ 1000,
32
+ 1000,
33
+ 1000,
34
+ 1000
35
+ ],
36
+ "special_tokens_map_file": null,
37
+ "tokenizer_class": "LayoutXLMTokenizer",
38
+ "unk_token": "<unk>"
39
+ }