gonzalobenegas commited on
Commit
352620e
1 Parent(s): eaa6a2b

Upload 3 files

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "[PAD]",
4
+ "unk_token": "[UNK]"
5
+ }
tokenizer.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[MASK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[UNK]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Lowercase"
36
+ },
37
+ "pre_tokenizer": {
38
+ "type": "Whitespace"
39
+ },
40
+ "post_processor": null,
41
+ "decoder": null,
42
+ "model": {
43
+ "type": "BPE",
44
+ "dropout": null,
45
+ "unk_token": "[UNK]",
46
+ "continuing_subword_prefix": null,
47
+ "end_of_word_suffix": null,
48
+ "fuse_unk": false,
49
+ "vocab": {
50
+ "[PAD]": 0,
51
+ "[MASK]": 1,
52
+ "[UNK]": 2,
53
+ "a": 3,
54
+ "c": 4,
55
+ "g": 5,
56
+ "t": 6
57
+ },
58
+ "merges": []
59
+ }
60
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "[PAD]",
4
+ "tokenizer_class": "PreTrainedTokenizerFast",
5
+ "unk_token": "[UNK]"
6
+ }