Hugging Face's logo

Synthyra
/
ESM2-650M

Fill-Mask
Transformers
Safetensors
fast_esm
custom_code
Model card Files
xet
 Community
1
lhallee commited on
Commit
8f2da6d
·
verified ·
1 Parent(s): 2a9607f

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer_config.json +53 -53
  2. vocab.txt +32 -32
tokenizer_config.json CHANGED
@@ -1,53 +1,53 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<cls>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<pad>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "<eos>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "<unk>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "32": {
36
- "content": "<mask>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "backend": "custom",
45
- "cls_token": "<cls>",
46
- "eos_token": "<eos>",
47
- "is_local": false,
48
- "mask_token": "<mask>",
49
- "model_max_length": 1000000000000000019884624838656,
50
- "pad_token": "<pad>",
51
- "tokenizer_class": "EsmTokenizer",
52
- "unk_token": "<unk>"
53
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<cls>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<eos>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "<cls>",
46
+ "eos_token": "<eos>",
47
+ "extra_special_tokens": {},
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "tokenizer_class": "EsmTokenizer",
52
+ "unk_token": "<unk>"
53
+ }
vocab.txt CHANGED
@@ -1,33 +1,33 @@
1
- <cls>
2
- <pad>
3
- <eos>
4
- <unk>
5
- L
6
- A
7
- G
8
- V
9
- S
10
- E
11
- R
12
- T
13
- I
14
- D
15
- P
16
- K
17
- Q
18
- N
19
- F
20
- Y
21
- M
22
- H
23
- W
24
- C
25
- X
26
- B
27
- U
28
- Z
29
- O
30
- .
31
- -
32
- <null_1>
33
  <mask>
 
1
+ <cls>
2
+ <pad>
3
+ <eos>
4
+ <unk>
5
+ L
6
+ A
7
+ G
8
+ V
9
+ S
10
+ E
11
+ R
12
+ T
13
+ I
14
+ D
15
+ P
16
+ K
17
+ Q
18
+ N
19
+ F
20
+ Y
21
+ M
22
+ H
23
+ W
24
+ C
25
+ X
26
+ B
27
+ U
28
+ Z
29
+ O
30
+ .
31
+ -
32
+ <null_1>
33
  <mask>