richardjonker2000 commited on
Commit
7a62628
·
verified ·
1 Parent(s): b3e82c4

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-large-uncased-abstract",
3
+ "architectures": [
4
+ "BertMultiHeadCRFModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "aug_prob": 0.5,
8
+ "augmentation": "random",
9
+ "bos_token_id": 0,
10
+ "classes": [
11
+ "SYMPTOM",
12
+ "PROCEDURE",
13
+ "DISEASE"
14
+ ],
15
+ "context_size": 64,
16
+ "crf_reduction": "mean",
17
+ "eos_token_ids": 0,
18
+ "freeze": false,
19
+ "hidden_act": "gelu",
20
+ "hidden_dropout_prob": 0.1,
21
+ "hidden_size": 1024,
22
+ "id2label": {
23
+ "0": "O",
24
+ "1": "B",
25
+ "2": "I"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 4096,
29
+ "label2id": {
30
+ "B": 1,
31
+ "I": 2,
32
+ "O": 0
33
+ },
34
+ "layer_norm_eps": 1e-12,
35
+ "max_position_embeddings": 512,
36
+ "model_type": "crf-tagger",
37
+ "num_attention_heads": 16,
38
+ "num_hidden_layers": 24,
39
+ "number_of_layer_per_head": 3,
40
+ "output_past": true,
41
+ "pad_token_id": 0,
42
+ "percentage_tags": 0.25,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.40.2",
45
+ "type_vocab_size": 2,
46
+ "version": "0.1.3",
47
+ "vocab_size": 28895
48
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b9b8001a0984a425fb1b7367713d88eecab316525a7e25010a5cbc89acb8e5
3
+ size 1367577344
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff