Minata commited on
Commit
17382a8
1 Parent(s): 777a1fa

Upload tokenizer

Browse files
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72f5d040a176945623a255484d24066f8c0da89a294359154e226efbe494b80
3
+ size 985833
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__java__",
4
+ "__python__",
5
+ "__en_XX__"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "language_codes": "base",
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 1024,
16
+ "name_or_path": "uclanlp/plbart-base",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "sp_model_kwargs": {},
20
+ "special_tokens_map_file": null,
21
+ "src_lang": null,
22
+ "tgt_lang": null,
23
+ "tokenizer_class": "PLBartTokenizer",
24
+ "unk_token": "<unk>"
25
+ }