Hugging Face's logo

AdrianBZG
/
tinyroberta-squad-es

Question Answering
Transformers
PyTorch
Safetensors
roberta
Inference Endpoints
Model card Files Community
AdrianBZG commited on
Commit
150819b
•
1 Parent(s): 39cf3a9

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +48 -55
tokenizer_config.json CHANGED
@@ -1,72 +1,65 @@
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
  "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
- "eos_token": {
21
- "__type": "AddedToken",
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false
27
- },
28
  "errors": "replace",
29
- "mask_token": {
30
- "__type": "AddedToken",
31
- "content": "<mask>",
32
- "lstrip": true,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
  "max_len": 512,
38
  "max_length": 384,
39
  "model_max_length": 512,
40
  "pad_to_multiple_of": null,
41
- "pad_token": {
42
- "__type": "AddedToken",
43
- "content": "<pad>",
44
- "lstrip": false,
45
- "normalized": true,
46
- "rstrip": false,
47
- "single_word": false
48
- },
49
  "pad_token_type_id": 0,
50
  "padding_side": "right",
51
- "sep_token": {
52
- "__type": "AddedToken",
53
- "content": "</s>",
54
- "lstrip": false,
55
- "normalized": true,
56
- "rstrip": false,
57
- "single_word": false
58
- },
59
  "stride": 128,
60
  "tokenizer_class": "RobertaTokenizer",
61
  "trim_offsets": true,
62
  "truncation_side": "right",
63
  "truncation_strategy": "only_second",
64
- "unk_token": {
65
- "__type": "AddedToken",
66
- "content": "<unk>",
67
- "lstrip": false,
68
- "normalized": true,
69
- "rstrip": false,
70
- "single_word": false
71
- }
72
  }
 
1
  {
2
  "add_prefix_space": true,
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": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  "errors": "replace",
50
+ "mask_token": "<mask>",
 
 
 
 
 
 
 
51
  "max_len": 512,
52
  "max_length": 384,
53
  "model_max_length": 512,
54
  "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
 
 
 
 
 
 
 
56
  "pad_token_type_id": 0,
57
  "padding_side": "right",
58
+ "sep_token": "</s>",
 
 
 
 
 
 
 
59
  "stride": 128,
60
  "tokenizer_class": "RobertaTokenizer",
61
  "trim_offsets": true,
62
  "truncation_side": "right",
63
  "truncation_strategy": "only_second",
64
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
65
  }