Rajashreee commited on
Commit
b58a4cd
1 Parent(s): b5e0b3c

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<cls>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "<sep>",
18
+ "unk_token": "<unk>"
19
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
3
+ size 798011
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "clean_up_tokenization_spaces": true,
8
+ "cls_token": "<cls>",
9
+ "do_lower_case": false,
10
+ "eos_token": "</s>",
11
+ "keep_accents": false,
12
+ "mask_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<mask>",
15
+ "lstrip": true,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": "<pad>",
22
+ "remove_space": true,
23
+ "sep_token": "<sep>",
24
+ "tokenizer_class": "XLNetTokenizer",
25
+ "unk_token": "<unk>"
26
+ }