Kendamarron commited on
Commit
9e9044b
1 Parent(s): 9d86e0b

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +21 -0
  2. spiece.model +3 -0
  3. tokenizer_config.json +77 -0
special_tokens_map.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<cls>",
4
+ "eos_token": {
5
+ "content": "</s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "mask_token": "<mask>",
12
+ "pad_token": "</s>",
13
+ "sep_token": "<sep>",
14
+ "unk_token": {
15
+ "content": "<unk>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ }
21
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5c56a739832923347681ed8a03a9cbf5afb6d1fe60089a5b01dd2dd063ab71
3
+ size 1208648
tokenizer_config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<sep>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<mask>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<cls>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "additional_special_tokens": [],
62
+ "bos_token": "<s>",
63
+ "clean_up_tokenization_spaces": true,
64
+ "cls_token": "<cls>",
65
+ "do_lower_case": false,
66
+ "eos_token": "</s>",
67
+ "extra_ids": 0,
68
+ "keep_accents": true,
69
+ "legacy": true,
70
+ "mask_token": "<mask>",
71
+ "model_max_length": 1000000000000000019884624838656,
72
+ "pad_token": "</s>",
73
+ "sep_token": "<sep>",
74
+ "sp_model_kwargs": {},
75
+ "tokenizer_class": "T5Tokenizer",
76
+ "unk_token": "<unk>"
77
+ }