Hugging Face's logo

STRIDE-lab
/
pubmedbert-setting-20250221

Text Classification
Transformers
Safetensors
PyTorch
English
bert
biomedical
text-embeddings-inference
Model card Files
xet
 Community
vera-bernhard commited on
Commit
fa885e1
·
verified ·
1 Parent(s): 4c73718

Initial model upload

Browse files
Files changed (8) hide show
  1. README.md +46 -0
  2. config.json +44 -0
  3. model.safetensors +3 -0
  4. params.json +20 -0
  5. special_tokens_map.json +7 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +58 -0
  8. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract
4
+ tags:
5
+ - transformers
6
+ - pytorch
7
+ - biomedical
8
+ - text-classification
9
+ ---
10
+
11
+ # pubmedbert_setting_20250221
12
+
13
+ Fine-tuned model from the PsyNamic project.
14
+
15
+ ## Base Model
16
+
17
+ `microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract`
18
+
19
+ ## Task
20
+
21
+ Setting
22
+
23
+ ## Training Parameters
24
+
25
+ ```json
26
+ {
27
+ "mode": "train",
28
+ "data": "<private_dataset>",
29
+ "task": "Setting",
30
+ "model": "pubmedbert",
31
+ "cross_val": false,
32
+ "batch_size": 8,
33
+ "learning_rate": 5e-05,
34
+ "weight_decay": 0.01,
35
+ "lr_scheduler": "linear",
36
+ "warmup_ratio": 0.1,
37
+ "epochs": 30,
38
+ "dropout": 0.1,
39
+ "early_stopping_patience": 5,
40
+ "gradient_clipping": 0.1,
41
+ "device": "cuda",
42
+ "load": null,
43
+ "max_length": 512,
44
+ "is_multilabel": true
45
+ }
46
+ ```
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
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": "Clinical",
13
+ "1": "Naturalistic",
14
+ "2": "Party setting",
15
+ "3": "Other setting",
16
+ "4": "Unknown",
17
+ "5": "Not applicable",
18
+ "6": "Palliative Setting"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "Clinical": "0",
24
+ "Naturalistic": "1",
25
+ "Not applicable": "5",
26
+ "Other setting": "3",
27
+ "Palliative Setting": "6",
28
+ "Party setting": "2",
29
+ "Unknown": "4"
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "multi_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.49.0",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 30522
44
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e68f2860f41f35326c36f4ada68ea529bc0acc82999f8601d73be200cb6dc8e9
3
+ size 437974028
params.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mode": "train",
3
+ "data": "<private_dataset>",
4
+ "task": "Setting",
5
+ "model": "pubmedbert",
6
+ "cross_val": false,
7
+ "batch_size": 8,
8
+ "learning_rate": 5e-05,
9
+ "weight_decay": 0.01,
10
+ "lr_scheduler": "linear",
11
+ "warmup_ratio": 0.1,
12
+ "epochs": 30,
13
+ "dropout": 0.1,
14
+ "early_stopping_patience": 5,
15
+ "gradient_clipping": 0.1,
16
+ "device": "cuda",
17
+ "load": null,
18
+ "max_length": 512,
19
+ "is_multilabel": true
20
+ }
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff