Trouter-Library commited on
Commit
6324379
·
verified ·
1 Parent(s): d38b312

Create tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +29 -0
tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|padding|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "<|endoftext|>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "model_max_length": 2048,
26
+ "pad_token": "<|padding|>",
27
+ "tokenizer_class": "GPTNeoXTokenizer",
28
+ "unk_token": "<|endoftext|>"
29
+ }