asahi417 commited on
Commit
ac11251
1 Parent(s): cf37f62

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +15 -1
  2. tokenizer.json +4 -2
  3. tokenizer_config.json +16 -1
special_tokens_map.json CHANGED
@@ -1 +1,15 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json CHANGED
@@ -53,7 +53,8 @@
53
  "pre_tokenizer": {
54
  "type": "ByteLevel",
55
  "add_prefix_space": false,
56
- "trim_offsets": true
 
57
  },
58
  "post_processor": {
59
  "type": "RobertaProcessing",
@@ -71,7 +72,8 @@
71
  "decoder": {
72
  "type": "ByteLevel",
73
  "add_prefix_space": true,
74
- "trim_offsets": true
 
75
  },
76
  "model": {
77
  "type": "BPE",
 
53
  "pre_tokenizer": {
54
  "type": "ByteLevel",
55
  "add_prefix_space": false,
56
+ "trim_offsets": true,
57
+ "use_regex": true
58
  },
59
  "post_processor": {
60
  "type": "RobertaProcessing",
 
72
  "decoder": {
73
  "type": "ByteLevel",
74
  "add_prefix_space": true,
75
+ "trim_offsets": true,
76
+ "use_regex": true
77
  },
78
  "model": {
79
  "type": "BPE",
tokenizer_config.json CHANGED
@@ -1 +1,16 @@
1
- {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "relbert-roberta-large-semeval2012-mask-prompt-b-nce", "tokenizer_class": "RobertaTokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "relbert-roberta-large-semeval2012-mask-prompt-b-nce",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }