taeshahn commited on
Commit
6178187
1 Parent(s): 7487521

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +14 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +14 -0
special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|sep|>",
5
+ "<|acc|>",
6
+ "<|tel|>",
7
+ "<|rrn|>",
8
+ "<|endofturn|>"
9
+ ],
10
+ "bos_token": "<|endoftext|>",
11
+ "eos_token": "<|endoftext|>",
12
+ "pad_token": "<|endoftext|>",
13
+ "unk_token": "<|endoftext|>"
14
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "<|endoftext|>",
4
+ "max_length": 512,
5
+ "model_max_length": 512,
6
+ "pad_to_multiple_of": null,
7
+ "pad_token": "<|endoftext|>",
8
+ "pad_token_type_id": 0,
9
+ "padding_side": "right",
10
+ "stride": 0,
11
+ "tokenizer_class": "PreTrainedTokenizerFast",
12
+ "truncation_side": "right",
13
+ "truncation_strategy": "longest_first"
14
+ }