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
1722473
·
verified ·
1 Parent(s): 9891794

Upload 6 files

Browse files
Files changed (6) hide show
  1. BGC_abundance_regression_model/model.safetensors +3 -0
  2. BGC_abundance_regression_model/regression_config.json +34 -0
  3. BGC_abundance_regression_model/special_tokens_map.json +44 -0
  4. BGC_abundance_regression_model/tokenizer_config.json +73 -0
  5. BGC_abundance_regression_model/training_args.bin +3 -0
  6. BGC_abundance_regression_model/vocab.txt +0 -0
BGC_abundance_regression_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2bc8b756f79c70303ff853449bfd1a87a9aef0f73b7424d5ee21032d34a400
3
+ size 1013148160
BGC_abundance_regression_model/regression_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_targets": 8,
3
+ "head": "mlp",
4
+ "hidden_size": 512,
5
+ "lstm_layers": 2,
6
+ "cnn_kernel": 3,
7
+ "dropout": 0.1,
8
+ "loss_type": "mse",
9
+ "huber_delta": 1.0,
10
+ "pretrained_dir": "/mnt/zzb/default/Workspace/jyzheng/models/model_3M_2048_v10/final_model",
11
+ "target_stats": {
12
+ "mean": [
13
+ 0.27447958386988835,
14
+ 0.4005759305638644,
15
+ 0.04693631303042901,
16
+ 0.8911714305993531,
17
+ 0.3163663648439005,
18
+ 0.8205084006773268,
19
+ 0.010180181093659695,
20
+ 1.61296046561147
21
+ ],
22
+ "std": [
23
+ 0.8426240485241817,
24
+ 1.508517090647771,
25
+ 0.25301948095119775,
26
+ 1.3785933353680424,
27
+ 0.8472574931688738,
28
+ 1.0853418828715786,
29
+ 0.10228318857711748,
30
+ 1.2825537097772675
31
+ ]
32
+ },
33
+ "max_length": 2048
34
+ }
BGC_abundance_regression_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
+ }
BGC_abundance_regression_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
+ }
BGC_abundance_regression_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e294a658622d3781e51bbcbbb0ae3b2d52247c281ace959e061eff7376d0ade8
3
+ size 5368
BGC_abundance_regression_model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff