canepunma commited on
Commit
7d2bf7b
1 Parent(s): 9365567

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +17 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +11 -0
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "max_length": 512,
6
+ "model_max_length": 2048,
7
+ "stride": 0,
8
+ "tokenizer_class": "PreTrainedTokenizerFast",
9
+ "truncation_side": "right",
10
+ "truncation_strategy": "longest_first"
11
+ }