mevol commited on
Commit
369f538
1 Parent(s): 76490f0

adding core files for protein structure model v2.1

Browse files
config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-chemical",
14
+ "2": "B-species",
15
+ "3": "B-gene",
16
+ "4": "I-gene",
17
+ "5": "B-taxonomy_domain",
18
+ "6": "I-chemical",
19
+ "7": "B-protein_type",
20
+ "8": "B-experimental_method",
21
+ "9": "I-experimental_method",
22
+ "10": "I-protein_type",
23
+ "11": "I-species",
24
+ "12": "B-evidence",
25
+ "13": "I-evidence",
26
+ "14": "B-protein",
27
+ "15": "I-protein",
28
+ "16": "B-protein_state",
29
+ "17": "B-site",
30
+ "18": "I-site",
31
+ "19": "B-structure_element",
32
+ "20": "I-structure_element",
33
+ "21": "B-complex_assembly",
34
+ "22": "I-protein_state",
35
+ "23": "I-complex_assembly",
36
+ "24": "B-ptm",
37
+ "25": "B-mutant",
38
+ "26": "I-mutant",
39
+ "27": "B-oligomeric_state",
40
+ "28": "B-residue_name_number",
41
+ "29": "B-bond_interaction",
42
+ "30": "I-bond_interaction",
43
+ "31": "B-residue_range",
44
+ "32": "I-residue_range",
45
+ "33": "B-residue_name",
46
+ "34": "B-residue_number",
47
+ "35": "I-ptm",
48
+ "36": "I-taxonomy_domain",
49
+ "37": "I-oligomeric_state",
50
+ "38": "I-residue_name_number",
51
+ "39": "I-residue_name",
52
+ "40": "I-residue_number"
53
+ },
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 3072,
56
+ "label2id": {
57
+ "B-bond_interaction": 29,
58
+ "B-chemical": 1,
59
+ "B-complex_assembly": 21,
60
+ "B-evidence": 12,
61
+ "B-experimental_method": 8,
62
+ "B-gene": 3,
63
+ "B-mutant": 25,
64
+ "B-oligomeric_state": 27,
65
+ "B-protein": 14,
66
+ "B-protein_state": 16,
67
+ "B-protein_type": 7,
68
+ "B-ptm": 24,
69
+ "B-residue_name": 33,
70
+ "B-residue_name_number": 28,
71
+ "B-residue_number": 34,
72
+ "B-residue_range": 31,
73
+ "B-site": 17,
74
+ "B-species": 2,
75
+ "B-structure_element": 19,
76
+ "B-taxonomy_domain": 5,
77
+ "I-bond_interaction": 30,
78
+ "I-chemical": 6,
79
+ "I-complex_assembly": 23,
80
+ "I-evidence": 13,
81
+ "I-experimental_method": 9,
82
+ "I-gene": 4,
83
+ "I-mutant": 26,
84
+ "I-oligomeric_state": 37,
85
+ "I-protein": 15,
86
+ "I-protein_state": 22,
87
+ "I-protein_type": 10,
88
+ "I-ptm": 35,
89
+ "I-residue_name": 39,
90
+ "I-residue_name_number": 38,
91
+ "I-residue_number": 40,
92
+ "I-residue_range": 32,
93
+ "I-site": 18,
94
+ "I-species": 11,
95
+ "I-structure_element": 20,
96
+ "I-taxonomy_domain": 36,
97
+ "O": 0
98
+ },
99
+ "layer_norm_eps": 1e-12,
100
+ "max_position_embeddings": 512,
101
+ "model_type": "bert",
102
+ "num_attention_heads": 12,
103
+ "num_hidden_layers": 12,
104
+ "pad_token_id": 0,
105
+ "position_embedding_type": "absolute",
106
+ "torch_dtype": "float32",
107
+ "transformers_version": "4.28.0",
108
+ "type_vocab_size": 2,
109
+ "use_cache": true,
110
+ "vocab_size": 30522
111
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744e186d0636f3c811a9fdfa80e5eaad38f89240a3afdde8d0762f2db0206dc9
3
+ size 435764845
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff