losyer8 commited on
Commit
e20a3b8
1 Parent(s): 872ef55

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +19 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +97 -0
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk|LLM-jp>",
4
+ "<s|LLM-jp>",
5
+ "</s|LLM-jp>",
6
+ "<mask|LLM-jp>",
7
+ "<pad|LLM-jp>",
8
+ "<CLS|LLM-jp>",
9
+ "<SEP|LLM-jp>",
10
+ "<EOD|LLM-jp>"
11
+ ],
12
+ "bos_token": "<s|LLM-jp>",
13
+ "cls_token": "<CLS|LLM-jp>",
14
+ "eos_token": "<EOD|LLM-jp>",
15
+ "mask_token": "<mask|LLM-jp>",
16
+ "pad_token": "<pad|LLM-jp>",
17
+ "sep_token": "<SEP|LLM-jp>",
18
+ "unk_token": "<unk|LLM-jp>"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk|LLM-jp>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s|LLM-jp>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s|LLM-jp>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<mask|LLM-jp>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<pad|LLM-jp>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<CLS|LLM-jp>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<SEP|LLM-jp>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<EOD|LLM-jp>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<unk|LLM-jp>",
70
+ "<s|LLM-jp>",
71
+ "</s|LLM-jp>",
72
+ "<mask|LLM-jp>",
73
+ "<pad|LLM-jp>",
74
+ "<CLS|LLM-jp>",
75
+ "<SEP|LLM-jp>",
76
+ "<EOD|LLM-jp>"
77
+ ],
78
+ "bos_token": "<s|LLM-jp>",
79
+ "clean_up_tokenization_spaces": true,
80
+ "cls_token": "<CLS|LLM-jp>",
81
+ "do_lower_case": false,
82
+ "eod_token": "<EOD|LLM-jp>",
83
+ "eos_token": "<EOD|LLM-jp>",
84
+ "extra_ids": 0,
85
+ "keep_accents": true,
86
+ "mask_token": "<mask|LLM-jp>",
87
+ "max_length": 2048,
88
+ "model_max_length": 1000000000000000019884624838656,
89
+ "pad_token": "<pad|LLM-jp>",
90
+ "sep_token": "<SEP|LLM-jp>",
91
+ "sp_model_kwargs": {},
92
+ "stride": 0,
93
+ "tokenizer_class": "PreTrainedTokenizerFast",
94
+ "truncation_side": "right",
95
+ "truncation_strategy": "longest_first",
96
+ "unk_token": "<unk|LLM-jp>"
97
+ }