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
ef5a8f9
·
verified ·
1 Parent(s): 41e7997

Upload 13 files

Browse files
Files changed (13) hide show
  1. model_140k_2048_v18/config.json +31 -0
  2. model_140k_2048_v18/model.safetensors +3 -0
  3. model_140k_2048_v18/model_config.json +18 -0
  4. model_140k_2048_v18/special_tokens_map.json +8 -0
  5. model_140k_2048_v18/tokenizer_config.json +73 -0
  6. model_140k_2048_v18/vocab.txt +0 -0
  7. model_3M_2048_v10/config.json +32 -0
  8. model_3M_2048_v10/generation_config.json +8 -0
  9. model_3M_2048_v10/model.safetensors +3 -0
  10. model_3M_2048_v10/model_config.json +18 -0
  11. model_3M_2048_v10/special_tokens_map.json +8 -0
  12. model_3M_2048_v10/tokenizer_config.json +73 -0
  13. model_3M_2048_v10/vocab.txt +0 -0
model_140k_2048_v18/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "cls_token_id": 2,
8
+ "eos_token_id": 3,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 512,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2048,
14
+ "layer_norm_eps": 1e-12,
15
+ "mask_token_id": 1,
16
+ "max_length": 2048,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "bert",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 6,
21
+ "pad_token_id": 0,
22
+ "position_embedding_type": "absolute",
23
+ "sep_token_id": 4,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.55.0",
27
+ "type_vocab_size": 1,
28
+ "unk_token_id": 5,
29
+ "use_cache": true,
30
+ "vocab_size": 146215
31
+ }
model_140k_2048_v18/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad068135df6c5872d75d81da2834bec6cab2c29df9543cb7d4c53d7cc881702
3
+ size 680406380
model_140k_2048_v18/model_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "BertForMaskedLM",
3
+ "hidden_size": 512,
4
+ "num_hidden_layers": 6,
5
+ "num_attention_heads": 8,
6
+ "intermediate_size": 2048,
7
+ "max_length": 2048,
8
+ "vocab_size": 146215,
9
+ "classification_config": {
10
+ "enabled": false,
11
+ "num_classes": null
12
+ },
13
+ "parameter_counts": {
14
+ "training_total_params": 170098471,
15
+ "core_model_params": 170098471,
16
+ "mlm_head_params": 0
17
+ }
18
+ }
model_140k_2048_v18/special_tokens_map.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "<cls>",
3
+ "eos_token": "<eos>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
6
+ "sep_token": "<sep>",
7
+ "unk_token": "<unk>"
8
+ }
model_140k_2048_v18/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
+ }
model_140k_2048_v18/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
model_3M_2048_v10/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "cls_token_id": 2,
8
+ "eos_token_id": 3,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2048,
14
+ "layer_norm_eps": 1e-12,
15
+ "mask_token_id": 1,
16
+ "max_length": 2048,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "bert",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 12,
21
+ "output_hidden_states": true,
22
+ "pad_token_id": 0,
23
+ "position_embedding_type": "absolute",
24
+ "sep_token_id": 4,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.53.2",
28
+ "type_vocab_size": 1,
29
+ "unk_token_id": 5,
30
+ "use_cache": true,
31
+ "vocab_size": 146215
32
+ }
model_3M_2048_v10/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "do_sample": false,
4
+ "num_beams": 1,
5
+ "early_stopping": false,
6
+ "pad_token_id": 0,
7
+ "eos_token_id": 3
8
+ }
model_3M_2048_v10/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6bece0a994094fefdcb0d38387fdd42d7000a92ac8f41faf0b560412474fadb
3
+ size 1614203540
model_3M_2048_v10/model_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "BertForMaskedLM",
3
+ "hidden_size": 1024,
4
+ "num_hidden_layers": 12,
5
+ "num_attention_heads": 16,
6
+ "intermediate_size": 4096,
7
+ "max_length": 2048,
8
+ "vocab_size": 146215,
9
+ "classification_config": {
10
+ "enabled": false,
11
+ "num_classes": null
12
+ },
13
+ "parameter_counts": {
14
+ "training_total_params": 403544871,
15
+ "core_model_params": 403544871,
16
+ "mlm_head_params": 0
17
+ }
18
+ }
model_3M_2048_v10/special_tokens_map.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "<cls>",
3
+ "eos_token": "<eos>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
6
+ "sep_token": "<sep>",
7
+ "unk_token": "<unk>"
8
+ }
model_3M_2048_v10/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
+ }
model_3M_2048_v10/vocab.txt ADDED
The diff for this file is too large to render. See raw diff