cakiki commited on
Commit
e96afb1
1 Parent(s): 6bd452d

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "unk_token": "[UNK]"
3
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "PreTrainedTokenizerFast",
3
+ "unk_token": "[UNK]",
4
+ "vocab_size": 70000
5
+ }