Hugging Face's logo

gplsi
/
Toxicity_model

Text Classification
Transformers
PyTorch
Safetensors
Spanish
roberta
Model card Files
xet
Community
2
amarmol commited on
Commit
c49b2bc
·
verified ·
1 Parent(s): fc00447

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +50 -57
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,66 +1,59 @@
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
- "clean_up_tokenization_spaces": true,
12
- "cls_token": {
13
- "__type": "AddedToken",
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false
19
- },
20
- "do_lower_case": false,
21
- "eos_token": {
22
- "__type": "AddedToken",
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": true,
26
- "rstrip": false,
27
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  },
 
 
 
 
29
  "errors": "replace",
30
- "mask_token": {
31
- "__type": "AddedToken",
32
- "content": "<mask>",
33
- "lstrip": true,
34
- "normalized": true,
35
- "rstrip": false,
36
- "single_word": false
37
- },
38
  "max_len": 512,
39
  "model_max_length": 512,
40
- "pad_token": {
41
- "__type": "AddedToken",
42
- "content": "<pad>",
43
- "lstrip": false,
44
- "normalized": true,
45
- "rstrip": false,
46
- "single_word": false
47
- },
48
- "sep_token": {
49
- "__type": "AddedToken",
50
- "content": "</s>",
51
- "lstrip": false,
52
- "normalized": true,
53
- "rstrip": false,
54
- "single_word": false
55
- },
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
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
  },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
  "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
 
 
 
 
 
 
52
  "max_len": 512,
53
  "model_max_length": 512,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  "tokenizer_class": "RobertaTokenizer",
57
  "trim_offsets": true,
58
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
59
  }