inu-ai commited on
Commit
4f03072
1 Parent(s): 542a1e6

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +9 -0
  2. spiece.model +3 -0
  3. tokenizer_config.json +16 -0
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "</s>",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "<unk>"
9
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dbbd4ddbe43941051ed35fd44ff0d9d1c00ed345f7fd4d1969df174110f0609
3
+ size 1044749
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "</s>",
8
+ "extra_ids": 0,
9
+ "mask_token": "[MASK]",
10
+ "model_max_length": 1000000000000000019884624838656,
11
+ "pad_token": "[PAD]",
12
+ "sep_token": "[SEP]",
13
+ "sp_model_kwargs": {},
14
+ "tokenizer_class": "T5Tokenizer",
15
+ "unk_token": "<unk>"
16
+ }