devnote5676 commited on
Commit
0c03897
·
1 Parent(s): d4f16af

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +6 -1
  2. tokenizer_config.json +4 -0
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
tokenizer_config.json CHANGED
@@ -137,11 +137,15 @@
137
  "cls_token": "[CLS]",
138
  "do_lower_case": true,
139
  "mask_token": "[MASK]",
 
140
  "model_max_length": 512,
141
  "pad_token": "[PAD]",
142
  "sep_token": "[SEP]",
 
143
  "strip_accents": null,
144
  "tokenize_chinese_chars": true,
145
  "tokenizer_class": "BertTokenizer",
 
 
146
  "unk_token": "[UNK]"
147
  }
 
137
  "cls_token": "[CLS]",
138
  "do_lower_case": true,
139
  "mask_token": "[MASK]",
140
+ "max_length": 512,
141
  "model_max_length": 512,
142
  "pad_token": "[PAD]",
143
  "sep_token": "[SEP]",
144
+ "stride": 0,
145
  "strip_accents": null,
146
  "tokenize_chinese_chars": true,
147
  "tokenizer_class": "BertTokenizer",
148
+ "truncation_side": "right",
149
+ "truncation_strategy": "longest_first",
150
  "unk_token": "[UNK]"
151
  }