wissamantoun commited on
Commit
89a8cc5
1 Parent(s): eb8e99a

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +52 -0
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "GPT2TokenizerFast",
3
+ "eos_token": {
4
+ "content": "<EOS>",
5
+ "single_word": false,
6
+ "lstrip": false,
7
+ "rstrip": false,
8
+ "normalized": false,
9
+ "__type": "AddedToken"
10
+ },
11
+ "unk_token": {
12
+ "content": "<UNK>",
13
+ "single_word": false,
14
+ "lstrip": false,
15
+ "rstrip": false,
16
+ "normalized": false,
17
+ "__type": "AddedToken"
18
+ },
19
+ "pad_token": {
20
+ "content": "<PAD>",
21
+ "single_word": false,
22
+ "lstrip": false,
23
+ "rstrip": false,
24
+ "normalized": false,
25
+ "__type": "AddedToken"
26
+ },
27
+ "bos_token": {
28
+ "content": "<EOS>",
29
+ "single_word": false,
30
+ "lstrip": false,
31
+ "rstrip": false,
32
+ "normalized": false,
33
+ "__type": "AddedToken"
34
+ },
35
+ "sep_token": {
36
+ "content": "<SEP>",
37
+ "single_word": false,
38
+ "lstrip": false,
39
+ "rstrip": false,
40
+ "normalized": false,
41
+ "__type": "AddedToken"
42
+ },
43
+ "mask_token": {
44
+ "content": "<MASK>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "__type": "AddedToken"
50
+ },
51
+ "model_max_length": 2048
52
+ }