wanadzhar913 commited on
Commit
441b842
1 Parent(s): f7ba7e4

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +43 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +62 -0
special_tokens_map.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<pad>",
4
+ "<s>",
5
+ "</s>",
6
+ "<unk>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "mask_token": {
23
+ "content": "_",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "pad_token": {
30
+ "content": "<pad>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "unk_token": {
37
+ "content": "<unk>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ }
43
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "66": {
36
+ "content": "_",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [
45
+ "<pad>",
46
+ "<s>",
47
+ "</s>",
48
+ "<unk>"
49
+ ],
50
+ "bos_token": "<s>",
51
+ "clean_up_tokenization_spaces": true,
52
+ "eos_token": "</s>",
53
+ "mask_token": "_",
54
+ "max_length": 16384,
55
+ "model_max_length": 1000000000000000019884624838656,
56
+ "pad_token": "<pad>",
57
+ "stride": 0,
58
+ "tokenizer_class": "PreTrainedTokenizerFast",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
+ }