cakiki commited on
Commit
a65ba5b
1 Parent(s): d68c5a4

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "name_or_path": "./toks/tokenizer/bytelevel-dropout-0.1-50K/",
3
+ "special_tokens_map_file": "./toks/tokenizer/bytelevel-dropout-0.1-50K/special_tokens_map.json",
4
+ "tokenizer_class": "PreTrainedTokenizerFast",
5
+ "vocab_size": 50000
6
+ }