Rajan Kumar commited on
Commit
fd8ca23
1 Parent(s): 4228b4f

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +16 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +11 -0
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
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
+ "model_input_names": [
6
+ "input_ids",
7
+ "attention_mask"
8
+ ],
9
+ "model_max_length": 2048,
10
+ "tokenizer_class": "PreTrainedTokenizerFast"
11
+ }