Hugging Face's logo

CamSaid
/
LED

Safetensors
led
Model card Files
xet
Community
CamSaid commited on
Commit
c5260b1
·
verified ·
1 Parent(s): 3b4bcf4

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +76 -64
tokenizer_config.json CHANGED
@@ -1,64 +1,76 @@
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
- "50264": {
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_length": 512,
52
- "model_max_length": 16384,
53
- "pad_to_multiple_of": null,
54
- "pad_token": "<pad>",
55
- "pad_token_type_id": 0,
56
- "padding_side": "right",
57
- "sep_token": "</s>",
58
- "stride": 0,
59
- "tokenizer_class": "LEDTokenizer",
60
- "trim_offsets": true,
61
- "truncation_side": "right",
62
- "truncation_strategy": "longest_first",
63
- "unk_token": "<unk>"
64
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50264": {
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_length": 512,
52
+ "model_max_length": 16384,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "tokenizer_class": "LEDTokenizer",
60
+ "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "<unk>",
64
+ "post_processor_class": "LEDTokenizerPostProcessor",
65
+ "post_processor": {
66
+ "type": "LedTokenizerPostProcessor",
67
+ "sep": {
68
+ "id": 2,
69
+ "token": "</s>"
70
+ },
71
+ "cls": {
72
+ "id": 0,
73
+ "token": "<s>"
74
+ }
75
+ }
76
+ }