Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +17 -0
- vocab.txt +30 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"full_tokenizer_file": null,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"name_or_path": "Rostlab/prot_bert",
|
9 |
+
"never_split": null,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
vocab.txt
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[PAD]
|
2 |
+
[UNK]
|
3 |
+
[CLS]
|
4 |
+
[SEP]
|
5 |
+
[MASK]
|
6 |
+
L
|
7 |
+
A
|
8 |
+
G
|
9 |
+
V
|
10 |
+
E
|
11 |
+
S
|
12 |
+
I
|
13 |
+
K
|
14 |
+
R
|
15 |
+
D
|
16 |
+
T
|
17 |
+
P
|
18 |
+
N
|
19 |
+
Q
|
20 |
+
F
|
21 |
+
Y
|
22 |
+
M
|
23 |
+
H
|
24 |
+
C
|
25 |
+
W
|
26 |
+
X
|
27 |
+
U
|
28 |
+
B
|
29 |
+
Z
|
30 |
+
O
|