mevol commited on
Commit
118b9e7
1 Parent(s): d5a931c

adding core files for protein structure model v1.2

Browse files
config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "B-experimental_method",
19
+ "7": "I-experimental_method",
20
+ "8": "B-protein_type",
21
+ "9": "I-protein_type",
22
+ "10": "I-species",
23
+ "11": "B-evidence",
24
+ "12": "I-evidence",
25
+ "13": "B-protein",
26
+ "14": "I-protein",
27
+ "15": "B-protein_state",
28
+ "16": "B-site",
29
+ "17": "I-site",
30
+ "18": "I-chemical",
31
+ "19": "B-complex_assembly",
32
+ "20": "I-complex_assembly",
33
+ "21": "I-protein_state",
34
+ "22": "B-ptm",
35
+ "23": "B-mutant",
36
+ "24": "I-mutant",
37
+ "25": "B-structure_element",
38
+ "26": "I-structure_element",
39
+ "27": "B-residue_range",
40
+ "28": "I-residue_range",
41
+ "29": "B-residue_name_number",
42
+ "30": "B-residue_name",
43
+ "31": "I-taxonomy_domain",
44
+ "32": "B-oligomeric_state",
45
+ "33": "I-oligomeric_state",
46
+ "34": "B-residue_number",
47
+ "35": "I-ptm",
48
+ "36": "I-residue_name_number",
49
+ "37": "I-residue_number"
50
+ },
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 3072,
53
+ "label2id": {
54
+ "B-chemical": 1,
55
+ "B-complex_assembly": 19,
56
+ "B-evidence": 11,
57
+ "B-experimental_method": 6,
58
+ "B-gene": 3,
59
+ "B-mutant": 23,
60
+ "B-oligomeric_state": 32,
61
+ "B-protein": 13,
62
+ "B-protein_state": 15,
63
+ "B-protein_type": 8,
64
+ "B-ptm": 22,
65
+ "B-residue_name": 30,
66
+ "B-residue_name_number": 29,
67
+ "B-residue_number": 34,
68
+ "B-residue_range": 27,
69
+ "B-site": 16,
70
+ "B-species": 2,
71
+ "B-structure_element": 25,
72
+ "B-taxonomy_domain": 5,
73
+ "I-chemical": 18,
74
+ "I-complex_assembly": 20,
75
+ "I-evidence": 12,
76
+ "I-experimental_method": 7,
77
+ "I-gene": 4,
78
+ "I-mutant": 24,
79
+ "I-oligomeric_state": 33,
80
+ "I-protein": 14,
81
+ "I-protein_state": 21,
82
+ "I-protein_type": 9,
83
+ "I-ptm": 35,
84
+ "I-residue_name_number": 36,
85
+ "I-residue_number": 37,
86
+ "I-residue_range": 28,
87
+ "I-site": 17,
88
+ "I-species": 10,
89
+ "I-structure_element": 26,
90
+ "I-taxonomy_domain": 31,
91
+ "O": 0
92
+ },
93
+ "layer_norm_eps": 1e-12,
94
+ "max_position_embeddings": 512,
95
+ "model_type": "bert",
96
+ "num_attention_heads": 12,
97
+ "num_hidden_layers": 12,
98
+ "pad_token_id": 0,
99
+ "position_embedding_type": "absolute",
100
+ "torch_dtype": "float32",
101
+ "transformers_version": "4.28.0",
102
+ "type_vocab_size": 2,
103
+ "use_cache": true,
104
+ "vocab_size": 30522
105
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13282ea39dc7a99a5d68378af7b6f5c7fc898575259f6d632f5ecdb68470cf4a
3
+ size 435755629
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