Junmai commited on
Commit
f438fbb
1 Parent(s): 464381a

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|sep|>",
5
+ "<|acc|>",
6
+ "<|tel|>",
7
+ "<|rrn|>"
8
+ ],
9
+ "bos_token": "<|unused1|>",
10
+ "eos_token": "<|endoftext|>",
11
+ "pad_token": "<|endoftext|>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "<|endoftext|>",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "<|endoftext|>",
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }