Hugging Face's logo

JINIAC
/
tokenizer_v0_9_ja42k_en13k_hi7k

Model card Files Community
u-10bei commited on
Commit
fc01454
•
1 Parent(s): 77eb92e

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +3 -0
  2. special_tokens_map.json +54 -0
  3. spiece.model +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +86 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<MASK>": 59528
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<EOD>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "cls_token": {
13
+ "content": "<CLS>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "mask_token": {
27
+ "content": "<MASK>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "<pad>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "sep_token": {
41
+ "content": "<SEP>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "unk_token": {
48
+ "content": "<unk>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ }
54
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf13ff3effdbc1c1b4ab80228b601a39ac7cef28f5469961fd3b6b83151e2e82
3
+ size 1068564
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "4": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "5": {
37
+ "content": "<CLS>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "6": {
45
+ "content": "<SEP>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "7": {
53
+ "content": "<EOD>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "59528": {
61
+ "content": "<MASK>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ }
68
+ },
69
+ "additional_special_tokens": [
70
+ "<EOD>"
71
+ ],
72
+ "bos_token": "<s>",
73
+ "clean_up_tokenization_spaces": true,
74
+ "cls_token": "<CLS>",
75
+ "eos_token": "</s>",
76
+ "extra_ids": 0,
77
+ "legacy": true,
78
+ "mask_token": "<MASK>",
79
+ "model_max_length": 2048,
80
+ "pad_token": "<pad>",
81
+ "sep_token": "<SEP>",
82
+ "sp_model_kwargs": {},
83
+ "split_special_tokens": true,
84
+ "tokenizer_class": "T5Tokenizer",
85
+ "unk_token": "<unk>"
86
+ }