This is the tokenizer used in the lucid prots project. The lower case letters represent the 3Di state of a residue introduced in the Foldseek paper.

Token Word
0 [PAD]
1 [UNK]
2 [CLS]
3 [SEP]
4 [MASK]
5 L
6 A
7 G
8 V
9 E
10 S
11 I
12 K
13 R
14 D
15 T
16 P
17 N
18 Q
19 F
20 Y
21 M
22 H
23 C
24 W
25 X
26 U
27 B
28 Z
29 O
30 a
31 c
32 d
33 e
34 f
35 g
36 h
37 i
38 k
39 l
40 m
41 n
42 p
43 q
44 r
45 s
46 t
47 v
48 w
49 y
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train adrianhenkel/lucid-prot-tokenizer