Hugging Face's logo

songlab
/
gpn-animal-promoter

Fill-Mask
Transformers
Safetensors
GPN
dna
variant-effect-prediction
biology
genomics
Inference Endpoints
Model card Files Community
gonzalobenegas commited on
Commit
4e43ecf
·
verified ·
1 Parent(s): 3bfcd8b

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +23 -0
  2. tokenizer.json +62 -0
  3. tokenizer_config.json +35 -0
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": {
3
+ "content": "[MASK]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "[PAD]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "byte_fallback": false,
50
+ "ignore_merges": false,
51
+ "vocab": {
52
+ "[PAD]": 0,
53
+ "[MASK]": 1,
54
+ "[UNK]": 2,
55
+ "a": 3,
56
+ "c": 4,
57
+ "g": 5,
58
+ "t": 6
59
+ },
60
+ "merges": []
61
+ }
62
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "extra_special_tokens": {},
30
+ "mask_token": "[MASK]",
31
+ "model_max_length": 1000000000000000019884624838656,
32
+ "pad_token": "[PAD]",
33
+ "tokenizer_class": "PreTrainedTokenizerFast",
34
+ "unk_token": "[UNK]"
35
+ }