WeixuanYuan commited on
Commit
59d7477
1 Parent(s): 869b9b4
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "[SYS]": 51272,
3
+ "[USR]": 51271
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[USR]",
4
+ "[SYS]"
5
+ ],
6
+ "bos_token": "[CLS]",
7
+ "cls_token": "[CLS]",
8
+ "eos_token": "[EOS]",
9
+ "mask_token": "[MASK]",
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "unk_token": "[UNK]"
13
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "eos_token": "[EOS]",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "name_or_path": "fnlp/bart-base-chinese",
10
+ "never_split": null,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "special_tokens_map_file": "vocab/cpt_v3_vocab/special_tokens_map.json",
14
+ "strip_accents": null,
15
+ "tokenize_chinese_chars": true,
16
+ "tokenizer_class": "BertTokenizer",
17
+ "unk_token": "[UNK]"
18
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff