hiroshi-matsuda-rit commited on
Commit
c156c5e
1 Parent(s): e20a3b8

Upload 3 files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +11 -17
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +12 -90
special_tokens_map.json CHANGED
@@ -1,19 +1,13 @@
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
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "</s|LLM-jp>"
4
+ ],
5
+ "bos_token": "<s|LLM-jp>",
6
+ "cls_token": "<CLS|LLM-jp>",
7
+ "eod_token": "<EOD|LLM-jp>",
8
+ "eos_token": "<EOD|LLM-jp>",
9
+ "mask_token": "<mask|LLM-jp>",
10
+ "pad_token": "<pad|LLM-jp>",
11
+ "sep_token": "<SEP|LLM-jp>",
12
+ "unk_token": "<unk|LLM-jp>"
 
 
 
 
 
 
13
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,97 +1,19 @@
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
  }
 
1
  {
2
+ "unk_token": "<unk|LLM-jp>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token": "<s|LLM-jp>",
 
 
 
 
4
  "eos_token": "<EOD|LLM-jp>",
 
 
 
 
 
5
  "pad_token": "<pad|LLM-jp>",
6
+ "cls_token": "<CLS|LLM-jp>",
7
  "sep_token": "<SEP|LLM-jp>",
8
+ "eod_token": "<EOD|LLM-jp>",
9
+ "mask_token": "<mask|LLM-jp>",
10
+ "extra_ids": 0,
11
+ "additional_special_tokens": [
12
+ "</s|LLM-jp>"
13
+ ],
14
  "sp_model_kwargs": {},
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "clean_up_tokenization_spaces": false,
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "PreTrainedTokenizerFast"
 
19
  }