Upload folder using huggingface_hub
Browse files- config.json +136 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +62 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/hps/nobackup/rdf/metagenomics/research-team/santiago/softw/trapiche_text/trapiche_text/data/multi_label_training/temp/domain_adapt_benchmark/microsoft-BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext-study-8_cv_fold-1/checkpoint-16200/",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
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": "root:Engineered:Biogas plant",
|
13 |
+
"1": "root:Engineered:Bioreactor",
|
14 |
+
"10": "root:Engineered:Solid waste",
|
15 |
+
"11": "root:Engineered:Wastewater",
|
16 |
+
"12": "root:Environmental:Air",
|
17 |
+
"13": "root:Environmental:Aquatic:Aquaculture",
|
18 |
+
"14": "root:Environmental:Aquatic:Estuary",
|
19 |
+
"15": "root:Environmental:Aquatic:Freshwater",
|
20 |
+
"16": "root:Environmental:Aquatic:Lentic",
|
21 |
+
"17": "root:Environmental:Aquatic:Marine",
|
22 |
+
"18": "root:Environmental:Aquatic:Meromictic lake",
|
23 |
+
"19": "root:Environmental:Aquatic:Non-marine Saline and Alkaline",
|
24 |
+
"2": "root:Engineered:Bioremediation",
|
25 |
+
"20": "root:Environmental:Aquatic:Sediment",
|
26 |
+
"21": "root:Environmental:Aquatic:Thermal springs",
|
27 |
+
"22": "root:Environmental:Terrestrial:Agricultural field",
|
28 |
+
"23": "root:Environmental:Terrestrial:Asphalt lakes",
|
29 |
+
"24": "root:Environmental:Terrestrial:Deep subsurface",
|
30 |
+
"25": "root:Environmental:Terrestrial:Geologic",
|
31 |
+
"26": "root:Environmental:Terrestrial:Oil reservoir",
|
32 |
+
"27": "root:Environmental:Terrestrial:Rock-dwelling (subaerial biofilm)",
|
33 |
+
"28": "root:Environmental:Terrestrial:Soil",
|
34 |
+
"29": "root:Environmental:Terrestrial:Volcanic",
|
35 |
+
"3": "root:Engineered:Biotransformation",
|
36 |
+
"30": "root:Host-associated:Algae",
|
37 |
+
"31": "root:Host-associated:Amphibia",
|
38 |
+
"32": "root:Host-associated:Animal",
|
39 |
+
"33": "root:Host-associated:Annelida",
|
40 |
+
"34": "root:Host-associated:Arthropoda",
|
41 |
+
"35": "root:Host-associated:Birds",
|
42 |
+
"36": "root:Host-associated:Cnidaria",
|
43 |
+
"37": "root:Host-associated:Echinodermata",
|
44 |
+
"38": "root:Host-associated:Endosymbionts",
|
45 |
+
"39": "root:Host-associated:Fish",
|
46 |
+
"4": "root:Engineered:Built environment",
|
47 |
+
"40": "root:Host-associated:Fungi",
|
48 |
+
"41": "root:Host-associated:Human",
|
49 |
+
"42": "root:Host-associated:Insecta",
|
50 |
+
"43": "root:Host-associated:Mammals",
|
51 |
+
"44": "root:Host-associated:Microbial",
|
52 |
+
"45": "root:Host-associated:Mollusca",
|
53 |
+
"46": "root:Host-associated:Plants",
|
54 |
+
"47": "root:Host-associated:Porifera",
|
55 |
+
"48": "root:Host-associated:Protists",
|
56 |
+
"49": "root:Host-associated:Protozoa",
|
57 |
+
"5": "root:Engineered:Food production",
|
58 |
+
"50": "root:Host-associated:Reptile",
|
59 |
+
"51": "root:Host-associated:Spiralia",
|
60 |
+
"52": "root:Host-associated:Tunicates",
|
61 |
+
"6": "root:Engineered:Industrial production",
|
62 |
+
"7": "root:Engineered:Lab Synthesis",
|
63 |
+
"8": "root:Engineered:Lab enrichment",
|
64 |
+
"9": "root:Engineered:Modeled"
|
65 |
+
},
|
66 |
+
"initializer_range": 0.02,
|
67 |
+
"intermediate_size": 3072,
|
68 |
+
"label2id": {
|
69 |
+
"root:Engineered:Biogas plant": "0",
|
70 |
+
"root:Engineered:Bioreactor": "1",
|
71 |
+
"root:Engineered:Bioremediation": "2",
|
72 |
+
"root:Engineered:Biotransformation": "3",
|
73 |
+
"root:Engineered:Built environment": "4",
|
74 |
+
"root:Engineered:Food production": "5",
|
75 |
+
"root:Engineered:Industrial production": "6",
|
76 |
+
"root:Engineered:Lab Synthesis": "7",
|
77 |
+
"root:Engineered:Lab enrichment": "8",
|
78 |
+
"root:Engineered:Modeled": "9",
|
79 |
+
"root:Engineered:Solid waste": "10",
|
80 |
+
"root:Engineered:Wastewater": "11",
|
81 |
+
"root:Environmental:Air": "12",
|
82 |
+
"root:Environmental:Aquatic:Aquaculture": "13",
|
83 |
+
"root:Environmental:Aquatic:Estuary": "14",
|
84 |
+
"root:Environmental:Aquatic:Freshwater": "15",
|
85 |
+
"root:Environmental:Aquatic:Lentic": "16",
|
86 |
+
"root:Environmental:Aquatic:Marine": "17",
|
87 |
+
"root:Environmental:Aquatic:Meromictic lake": "18",
|
88 |
+
"root:Environmental:Aquatic:Non-marine Saline and Alkaline": "19",
|
89 |
+
"root:Environmental:Aquatic:Sediment": "20",
|
90 |
+
"root:Environmental:Aquatic:Thermal springs": "21",
|
91 |
+
"root:Environmental:Terrestrial:Agricultural field": "22",
|
92 |
+
"root:Environmental:Terrestrial:Asphalt lakes": "23",
|
93 |
+
"root:Environmental:Terrestrial:Deep subsurface": "24",
|
94 |
+
"root:Environmental:Terrestrial:Geologic": "25",
|
95 |
+
"root:Environmental:Terrestrial:Oil reservoir": "26",
|
96 |
+
"root:Environmental:Terrestrial:Rock-dwelling (subaerial biofilm)": "27",
|
97 |
+
"root:Environmental:Terrestrial:Soil": "28",
|
98 |
+
"root:Environmental:Terrestrial:Volcanic": "29",
|
99 |
+
"root:Host-associated:Algae": "30",
|
100 |
+
"root:Host-associated:Amphibia": "31",
|
101 |
+
"root:Host-associated:Animal": "32",
|
102 |
+
"root:Host-associated:Annelida": "33",
|
103 |
+
"root:Host-associated:Arthropoda": "34",
|
104 |
+
"root:Host-associated:Birds": "35",
|
105 |
+
"root:Host-associated:Cnidaria": "36",
|
106 |
+
"root:Host-associated:Echinodermata": "37",
|
107 |
+
"root:Host-associated:Endosymbionts": "38",
|
108 |
+
"root:Host-associated:Fish": "39",
|
109 |
+
"root:Host-associated:Fungi": "40",
|
110 |
+
"root:Host-associated:Human": "41",
|
111 |
+
"root:Host-associated:Insecta": "42",
|
112 |
+
"root:Host-associated:Mammals": "43",
|
113 |
+
"root:Host-associated:Microbial": "44",
|
114 |
+
"root:Host-associated:Mollusca": "45",
|
115 |
+
"root:Host-associated:Plants": "46",
|
116 |
+
"root:Host-associated:Porifera": "47",
|
117 |
+
"root:Host-associated:Protists": "48",
|
118 |
+
"root:Host-associated:Protozoa": "49",
|
119 |
+
"root:Host-associated:Reptile": "50",
|
120 |
+
"root:Host-associated:Spiralia": "51",
|
121 |
+
"root:Host-associated:Tunicates": "52"
|
122 |
+
},
|
123 |
+
"layer_norm_eps": 1e-12,
|
124 |
+
"max_position_embeddings": 512,
|
125 |
+
"model_type": "bert",
|
126 |
+
"num_attention_heads": 12,
|
127 |
+
"num_hidden_layers": 12,
|
128 |
+
"pad_token_id": 0,
|
129 |
+
"position_embedding_type": "absolute",
|
130 |
+
"problem_type": "multi_label_classification",
|
131 |
+
"torch_dtype": "float32",
|
132 |
+
"transformers_version": "4.48.3",
|
133 |
+
"type_vocab_size": 2,
|
134 |
+
"use_cache": true,
|
135 |
+
"vocab_size": 30522
|
136 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f8b5269a8a3dbc74c01b5572e4182e027c635b0a6d4f0de63a68692fe12249
|
3 |
+
size 438115524
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "[UNK]",
|
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": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"max_length": 256,
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"never_split": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"stride": 0,
|
56 |
+
"strip_accents": null,
|
57 |
+
"tokenize_chinese_chars": true,
|
58 |
+
"tokenizer_class": "BertTokenizer",
|
59 |
+
"truncation_side": "right",
|
60 |
+
"truncation_strategy": "longest_first",
|
61 |
+
"unk_token": "[UNK]"
|
62 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|