mjbommar commited on
Commit
cdeef3f
·
verified ·
1 Parent(s): 388bd46

Upload OGBert v1 MLM tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +26 -0
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|start|>",
5
+ "cls_token": "<|cls|>",
6
+ "eos_token": "<|end|>",
7
+ "extra_special_tokens": [],
8
+ "is_local": true,
9
+ "mask_token": "<|mask|>",
10
+ "model_max_length": 1024,
11
+ "pad_token": "<|pad|>",
12
+ "padding_side": "right",
13
+ "sep_token": "<|sep|>",
14
+ "special_tokens_map": {
15
+ "bos_token": "<|start|>",
16
+ "cls_token": "<|cls|>",
17
+ "eos_token": "<|end|>",
18
+ "mask_token": "<|mask|>",
19
+ "pad_token": "<|pad|>",
20
+ "sep_token": "<|sep|>",
21
+ "unk_token": "<|unk|>"
22
+ },
23
+ "tokenizer_class": "TokenizersBackend",
24
+ "truncation": "longest_first",
25
+ "unk_token": "<|unk|>"
26
+ }