Upload 12 files
Browse files- BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext/config.json +17 -0
- BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext/tokenizer_config.json +3 -0
- BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext/vocab.txt +0 -0
- CLAProt_650M_UniRef50.pt +3 -0
- esm2_t33_650M_UR50D/config.json +26 -0
- esm2_t33_650M_UR50D/special_tokens_map.json +7 -0
- esm2_t33_650M_UR50D/tokenizer_config.json +3 -0
- esm2_t33_650M_UR50D/vocab.txt +33 -0
- foldseek_t30_150M/config.json +30 -0
- foldseek_t30_150M/special_tokens_map.json +7 -0
- foldseek_t30_150M/tokenizer_config.json +3 -0
- foldseek_t30_150M/vocab.txt +26 -0
BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext/config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForMaskedLM"
|
4 |
+
],
|
5 |
+
"model_type": "bert",
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"num_attention_heads": 12,
|
14 |
+
"num_hidden_layers": 12,
|
15 |
+
"type_vocab_size": 2,
|
16 |
+
"vocab_size": 30522
|
17 |
+
}
|
BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext/tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lower_case": true
|
3 |
+
}
|
BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
CLAProt_650M_UniRef50.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:578b1e15d1a9468bbdb23731d09e2c2243c1527eb2c99acf10fb3eccf2299052
|
3 |
+
size 3644110313
|
esm2_t33_650M_UR50D/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"EsmForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.0,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"emb_layer_norm_before": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 1280,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 5120,
|
13 |
+
"layer_norm_eps": 1e-05,
|
14 |
+
"mask_token_id": 32,
|
15 |
+
"max_position_embeddings": 1026,
|
16 |
+
"model_type": "esm",
|
17 |
+
"num_attention_heads": 20,
|
18 |
+
"num_hidden_layers": 33,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"position_embedding_type": "rotary",
|
21 |
+
"token_dropout": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.23.0.dev0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 33
|
26 |
+
}
|
esm2_t33_650M_UR50D/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "<cls>",
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
esm2_t33_650M_UR50D/tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"tokenizer_class": "EsmTokenizer"
|
3 |
+
}
|
esm2_t33_650M_UR50D/vocab.txt
ADDED
@@ -0,0 +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>
|
foldseek_t30_150M/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/tmp/facebook/esm2_t30_150M_UR50D",
|
3 |
+
"architectures": [
|
4 |
+
"EsmForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_layer_norm_before": false,
|
9 |
+
"esmfold_config": null,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 640,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 2560,
|
15 |
+
"is_folding_model": false,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"mask_token_id": 4,
|
18 |
+
"max_position_embeddings": 1026,
|
19 |
+
"model_type": "esm",
|
20 |
+
"num_attention_heads": 20,
|
21 |
+
"num_hidden_layers": 30,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "rotary",
|
24 |
+
"token_dropout": true,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.25.0.dev0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_list": null,
|
29 |
+
"vocab_size": 26
|
30 |
+
}
|
foldseek_t30_150M/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "<cls>",
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
foldseek_t30_150M/tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"tokenizer_class": "EsmTokenizer"
|
3 |
+
}
|
foldseek_t30_150M/vocab.txt
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<cls>
|
2 |
+
<pad>
|
3 |
+
<eos>
|
4 |
+
<unk>
|
5 |
+
<mask>
|
6 |
+
p
|
7 |
+
y
|
8 |
+
n
|
9 |
+
w
|
10 |
+
r
|
11 |
+
q
|
12 |
+
h
|
13 |
+
g
|
14 |
+
d
|
15 |
+
l
|
16 |
+
v
|
17 |
+
t
|
18 |
+
m
|
19 |
+
f
|
20 |
+
s
|
21 |
+
a
|
22 |
+
e
|
23 |
+
i
|
24 |
+
k
|
25 |
+
c
|
26 |
+
#
|