Hugging Face's logo

SantoshAdabala
/
ClinicalFlamo

Token Classification
Transformers
Safetensors
ONNX
English
bert
clinical-nlp
named-entity-recognition
ner
biomedical
knowledge-distillation
phi-detection
quantization
Eval Results (legacy)
Model card Files
xet
 Community
SantoshAdabala commited on
Commit
bdf0c5e
·
verified ·
1 Parent(s): 43b0492

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +27 -15
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +56 -0
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,9 +1,19 @@
1
  {
 
 
 
 
 
 
2
  "architectures": [
3
- "DistilBertForTokenClassification"
4
  ],
5
- "model_type": "distilbert",
6
- "num_labels": 5,
 
 
 
 
7
  "id2label": {
8
  "0": "O",
9
  "1": "B-Chemical",
@@ -11,22 +21,24 @@
11
  "3": "B-Disease",
12
  "4": "I-Disease"
13
  },
 
 
14
  "label2id": {
15
- "O": 0,
16
  "B-Chemical": 1,
17
- "I-Chemical": 2,
18
  "B-Disease": 3,
19
- "I-Disease": 4
 
 
20
  },
21
- "hidden_size": 768,
22
  "max_position_embeddings": 512,
 
23
  "num_attention_heads": 12,
24
  "num_hidden_layers": 6,
25
- "task_specific_params": {
26
- "ner": {
27
- "dataset": "BC5CDR",
28
- "macro_f1": 0.807,
29
- "f1_retention": 0.932
30
- }
31
- }
32
- }
 
1
  {
2
+ "adapters": {
3
+ "adapters": {},
4
+ "config_map": {},
5
+ "fusion_config_map": {},
6
+ "fusions": {}
7
+ },
8
  "architectures": [
9
+ "BertForTokenClassification"
10
  ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "classifier_dropout": null,
13
+ "dtype": "float32",
14
+ "hidden_act": "gelu",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 768,
17
  "id2label": {
18
  "0": "O",
19
  "1": "B-Chemical",
 
21
  "3": "B-Disease",
22
  "4": "I-Disease"
23
  },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
  "label2id": {
 
27
  "B-Chemical": 1,
 
28
  "B-Disease": 3,
29
+ "I-Chemical": 2,
30
+ "I-Disease": 4,
31
+ "O": 0
32
  },
33
+ "layer_norm_eps": 1e-12,
34
  "max_position_embeddings": 512,
35
+ "model_type": "bert",
36
  "num_attention_heads": 12,
37
  "num_hidden_layers": 6,
38
+ "pad_token_id": 0,
39
+ "position_embedding_type": "absolute",
40
+ "transformers_version": "4.57.6",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 28996
44
+ }
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0743ff17c9f82da0dab9c9b848d97e41daa66d25cd097bf6b30d3047912aab3f
3
+ size 260797180
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff