toanbku commited on
Commit
9517c0d
1 Parent(s): 0e93346

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|prompter|>",
4
+ ">>SUFFIX<<",
5
+ "<|prefix_begin|>",
6
+ ">>INTRODUCTION<<",
7
+ ">>QUESTION<<",
8
+ ">>SUMMARY<<",
9
+ "<|prefix_end|>",
10
+ ">>DOMAIN<<",
11
+ "<|assistant|>",
12
+ "<|system|>",
13
+ ">>TITLE<<",
14
+ ">>COMMENT<<",
15
+ ">>MIDDLE<<",
16
+ ">>PREFIX<<",
17
+ ">>ANSWER<<",
18
+ ">>ABSTRACT<<"
19
+ ],
20
+ "eos_token": "<|endoftext|>",
21
+ "pad_token": "<|endoftext|>",
22
+ "sep_token": "<|endoftext|>"
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "special_tokens_map_file": null,
7
+ "tokenizer_class": "PreTrainedTokenizerFast"
8
+ }