limajr commited on
Commit
c21998a
·
verified ·
1 Parent(s): 0306983

Upload tokenizer NBR-500

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "model_max_length": 2048,
5
+ "tokenizer_class": "PreTrainedTokenizerFast",
6
+ "bos_token": "<s>",
7
+ "eos_token": "</s>",
8
+ "unk_token": "<unk>",
9
+ "pad_token": "<pad>"
10
+ }