Hugging Face's logo

numind
/
NuNER-v1.0

Token Classification
Transformers
Safetensors
English
roberta
feature-extraction
entity-recognition
foundation-model
RoBERTa
generic
Model card Files Community
1
Serega6678 commited on
Commit
ef9bb2f
•
1 Parent(s): 9fcf0ba

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +43 -7
  2. tokenizer.json +1 -1
  3. tokenizer_config.json +1 -1
special_tokens_map.json CHANGED
@@ -1,15 +1,51 @@
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
  }
 
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
@@ -45,7 +45,7 @@
45
  "single_word": false,
46
  "lstrip": true,
47
  "rstrip": false,
48
- "normalized": false,
49
  "special": true
50
  }
51
  ],
 
45
  "single_word": false,
46
  "lstrip": true,
47
  "rstrip": false,
48
+ "normalized": true,
49
  "special": true
50
  }
51
  ],
tokenizer_config.json CHANGED
@@ -36,7 +36,7 @@
36
  "50264": {
37
  "content": "<mask>",
38
  "lstrip": true,
39
- "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
 
36
  "50264": {
37
  "content": "<mask>",
38
  "lstrip": true,
39
+ "normalized": true,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true