mevol commited on
Commit
2ddc766
1 Parent(s): 0f187e1

Upload 4 files

Browse files

adding the core files for the finetuned model

Files changed (4) hide show
  1. config.json +121 -0
  2. pytorch_model.bin +3 -0
  3. tokenizer_config.json +15 -0
  4. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-location",
32
+ "20": "I-location",
33
+ "21": "B-complex_assembly",
34
+ "22": "I-complex_assembly",
35
+ "23": "I-protein_state",
36
+ "24": "B-stoichiometry",
37
+ "25": "B-ptm",
38
+ "26": "B-mutant",
39
+ "27": "I-mutant",
40
+ "28": "B-structure_element",
41
+ "29": "I-structure_element",
42
+ "30": "B-residue_range",
43
+ "31": "I-residue_range",
44
+ "32": "B-residue_name_number",
45
+ "33": "B-non_covalent_bond",
46
+ "34": "I-non_covalent_bond",
47
+ "35": "B-residue_name",
48
+ "36": "B-oligomeric_state",
49
+ "37": "I-taxonomy_domain",
50
+ "38": "I-oligomeric_state",
51
+ "39": "I-stoichiometry",
52
+ "40": "B-residue_number",
53
+ "41": "I-ptm",
54
+ "42": "B-covalent_bond",
55
+ "43": "I-covalent_bond",
56
+ "44": "I-residue_name_number",
57
+ "45": "I-residue_number"
58
+ },
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 3072,
61
+ "label2id": {
62
+ "B-chemical": 1,
63
+ "B-complex_assembly": 21,
64
+ "B-covalent_bond": 42,
65
+ "B-evidence": 11,
66
+ "B-experimental_method": 6,
67
+ "B-gene": 3,
68
+ "B-location": 19,
69
+ "B-mutant": 26,
70
+ "B-non_covalent_bond": 33,
71
+ "B-oligomeric_state": 36,
72
+ "B-protein": 13,
73
+ "B-protein_state": 15,
74
+ "B-protein_type": 8,
75
+ "B-ptm": 25,
76
+ "B-residue_name": 35,
77
+ "B-residue_name_number": 32,
78
+ "B-residue_number": 40,
79
+ "B-residue_range": 30,
80
+ "B-site": 16,
81
+ "B-species": 2,
82
+ "B-stoichiometry": 24,
83
+ "B-structure_element": 28,
84
+ "B-taxonomy_domain": 5,
85
+ "I-chemical": 18,
86
+ "I-complex_assembly": 22,
87
+ "I-covalent_bond": 43,
88
+ "I-evidence": 12,
89
+ "I-experimental_method": 7,
90
+ "I-gene": 4,
91
+ "I-location": 20,
92
+ "I-mutant": 27,
93
+ "I-non_covalent_bond": 34,
94
+ "I-oligomeric_state": 38,
95
+ "I-protein": 14,
96
+ "I-protein_state": 23,
97
+ "I-protein_type": 9,
98
+ "I-ptm": 41,
99
+ "I-residue_name_number": 44,
100
+ "I-residue_number": 45,
101
+ "I-residue_range": 31,
102
+ "I-site": 17,
103
+ "I-species": 10,
104
+ "I-stoichiometry": 39,
105
+ "I-structure_element": 29,
106
+ "I-taxonomy_domain": 37,
107
+ "O": 0
108
+ },
109
+ "layer_norm_eps": 1e-12,
110
+ "max_position_embeddings": 512,
111
+ "model_type": "bert",
112
+ "num_attention_heads": 12,
113
+ "num_hidden_layers": 12,
114
+ "pad_token_id": 0,
115
+ "position_embedding_type": "absolute",
116
+ "torch_dtype": "float32",
117
+ "transformers_version": "4.28.1",
118
+ "type_vocab_size": 2,
119
+ "use_cache": true,
120
+ "vocab_size": 30522
121
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51c7eb04784772caa4630471cd00d48af7162dd5ced5458bd4383b6ec325c54f
3
+ size 435780205
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