itay-nakash commited on
Commit
a717674
1 Parent(s): a8dcf9a

Upload tokenizer

Browse files
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<cls>",
5
+ "eos_token": "</s>",
6
+ "mask_token": "<mask>",
7
+ "model_max_length": 128,
8
+ "pad_token": "<pad>",
9
+ "sep_token": "<sep>",
10
+ "special_tokens_map_file": "/data/home/itay.nakash/cramming_w_elad/cramming_playground/outputs/baseline_new/checkpoints/ScriptableCrammedBERT_2023-08-08_2.0925/special_tokens_map.json",
11
+ "tokenizer_class": "PreTrainedTokenizerFast",
12
+ "unk_token": "<unk>"
13
+ }