Hugging Face's logo

jackkuo
/
Orthoformer

Feature Extraction
Safetensors
English
genomics
microbiome
foundation-model
functional-embedding
orthology
Model card Files
xet
 Community
jackkuo commited on
Commit
6dd9576
·
verified ·
1 Parent(s): fc05174

Upload 6 files

Browse files
Files changed (6) hide show
  1. Orthoformer_CRISPR_model/model.safetensors +3 -0
  2. Orthoformer_CRISPR_model/special_tokens_map.json +44 -0
  3. Orthoformer_CRISPR_model/token_multiclass_config.json +23 -0
  4. Orthoformer_CRISPR_model/tokenizer_config.json +73 -0
  5. Orthoformer_CRISPR_model/training_args.bin +3 -0
  6. Orthoformer_CRISPR_model/vocab.txt +0 -0
Orthoformer_CRISPR_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e8732cda9a04606968df4f0a877fc13a55933d8588f3d64ac908e816c1b795
3
+ size 1027343104
Orthoformer_CRISPR_model/special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "<cls>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "<sep>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "<unk>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
Orthoformer_CRISPR_model/token_multiclass_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_labels": 8,
3
+ "head": "bilstm",
4
+ "hidden_size": 512,
5
+ "lstm_layers": 2,
6
+ "cnn_kernel": 3,
7
+ "dropout": 0.1,
8
+ "loss_type": "focal",
9
+ "focal_gamma": 3.0,
10
+ "focal_alpha": null,
11
+ "ignore_index": -100,
12
+ "class_counts": null,
13
+ "used_class_weights": [
14
+ 1.0007794368024594,
15
+ 29.767523186347972,
16
+ 87.31232558456517,
17
+ 65.79508827548975,
18
+ 327.1933632819917,
19
+ 185.50711435518195,
20
+ 469.9219536057797,
21
+ 206.6028777376934
22
+ ]
23
+ }
Orthoformer_CRISPR_model/tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<mask>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<cls>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<eos>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<sep>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<unk>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "clean_up_tokenization_spaces": true,
53
+ "cls_token": "<cls>",
54
+ "do_basic_tokenize": true,
55
+ "do_lower_case": false,
56
+ "eos_token": "<eos>",
57
+ "extra_special_tokens": {},
58
+ "mask_token": "<mask>",
59
+ "model_input_names": [
60
+ "input_ids",
61
+ "attention_mask"
62
+ ],
63
+ "model_max_length": 2048,
64
+ "never_split": null,
65
+ "pad_token": "<pad>",
66
+ "padding_side": "right",
67
+ "sep_token": "<sep>",
68
+ "strip_accents": null,
69
+ "tokenize_chinese_chars": true,
70
+ "tokenizer_class": "BertTokenizer",
71
+ "unk_token": "<unk>",
72
+ "use_fast": false
73
+ }
Orthoformer_CRISPR_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d20d3aab608eff086e51975d0a514170cfe844b49177ee0d2ff0f95f3a90dd
3
+ size 5432
Orthoformer_CRISPR_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff