kobkrit commited on
Commit
d221787
1 Parent(s): e0e214c

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +5 -0
  2. spiece.model +3 -0
  3. tokenizer_config.json +11 -0
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c762bb8b5f8fbf3752db14081c03b208461797326fc28793388e41bceeaf08f3
3
+ size 783789
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "</s>",
5
+ "extra_ids": 0,
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "sp_model_kwargs": {},
9
+ "tokenizer_class": "T5Tokenizer",
10
+ "unk_token": "<unk>"
11
+ }