Upload tokenizer
Browse files- dna_vocab_list.txt +2 -31
- protein_vocab_list.txt +34 -0
dna_vocab_list.txt
CHANGED
|
@@ -1,34 +1,5 @@
|
|
| 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 |
-
|
| 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>
|
| 34 |
-
<bos>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
A
|
| 2 |
+
C
|
| 3 |
G
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
T
|
| 5 |
+
<unk>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
protein_vocab_list.txt
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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>
|
| 34 |
+
<bos>
|