Hugging Face's logo

BSC-NLP4BIA
/
bsc-bio-ehr-es-meddocan

Token Classification
Transformers
PyTorch
Spanish
roberta
biomedical
clinical
EHR
spanish
anonymization
Eval Results
Inference Endpoints
Model card Files Community
1
janrodriguez commited on
Commit
184b49c
•
1 Parent(s): a04286b

Initial commit

Browse files
Files changed (8) hide show
  1. config.json +122 -0
  2. merges.txt +0 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +65 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/bsc-bio-ehr-es",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.5,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "B-CALLE",
17
+ "2": "I-CALLE",
18
+ "3": "B-CENTRO_SALUD",
19
+ "4": "I-CENTRO_SALUD",
20
+ "5": "B-CORREO_ELECTRONICO",
21
+ "6": "I-CORREO_ELECTRONICO",
22
+ "7": "B-EDAD_SUJETO_ASISTENCIA",
23
+ "8": "I-EDAD_SUJETO_ASISTENCIA",
24
+ "9": "B-FAMILIARES_SUJETO_ASISTENCIA",
25
+ "10": "I-FAMILIARES_SUJETO_ASISTENCIA",
26
+ "11": "B-FECHAS",
27
+ "12": "I-FECHAS",
28
+ "13": "B-HOSPITAL",
29
+ "14": "I-HOSPITAL",
30
+ "15": "B-ID_ASEGURAMIENTO",
31
+ "16": "I-ID_ASEGURAMIENTO",
32
+ "17": "B-ID_CONTACTO_ASISTENCIAL",
33
+ "18": "I-ID_CONTACTO_ASISTENCIAL",
34
+ "19": "B-ID_EMPLEO_PERSONAL_SANITARIO",
35
+ "20": "I-ID_EMPLEO_PERSONAL_SANITARIO",
36
+ "21": "B-ID_SUJETO_ASISTENCIA",
37
+ "22": "I-ID_SUJETO_ASISTENCIA",
38
+ "23": "B-ID_TITULACION_PERSONAL_SANITARIO",
39
+ "24": "I-ID_TITULACION_PERSONAL_SANITARIO",
40
+ "25": "B-INSTITUCION",
41
+ "26": "I-INSTITUCION",
42
+ "27": "B-NOMBRE_PERSONAL_SANITARIO",
43
+ "28": "I-NOMBRE_PERSONAL_SANITARIO",
44
+ "29": "B-NOMBRE_SUJETO_ASISTENCIA",
45
+ "30": "I-NOMBRE_SUJETO_ASISTENCIA",
46
+ "31": "B-NUMERO_FAX",
47
+ "32": "I-NUMERO_FAX",
48
+ "33": "B-NUMERO_TELEFONO",
49
+ "34": "I-NUMERO_TELEFONO",
50
+ "35": "B-OTROS_SUJETO_ASISTENCIA",
51
+ "36": "I-OTROS_SUJETO_ASISTENCIA",
52
+ "37": "B-PAIS",
53
+ "38": "I-PAIS",
54
+ "39": "B-PROFESION",
55
+ "40": "I-PROFESION",
56
+ "41": "B-SEXO_SUJETO_ASISTENCIA",
57
+ "42": "I-SEXO_SUJETO_ASISTENCIA",
58
+ "43": "B-TERRITORIO",
59
+ "44": "I-TERRITORIO"
60
+ },
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 3072,
63
+ "label2id": {
64
+ "B-CALLE": 1,
65
+ "B-CENTRO_SALUD": 3,
66
+ "B-CORREO_ELECTRONICO": 5,
67
+ "B-EDAD_SUJETO_ASISTENCIA": 7,
68
+ "B-FAMILIARES_SUJETO_ASISTENCIA": 9,
69
+ "B-FECHAS": 11,
70
+ "B-HOSPITAL": 13,
71
+ "B-ID_ASEGURAMIENTO": 15,
72
+ "B-ID_CONTACTO_ASISTENCIAL": 17,
73
+ "B-ID_EMPLEO_PERSONAL_SANITARIO": 19,
74
+ "B-ID_SUJETO_ASISTENCIA": 21,
75
+ "B-ID_TITULACION_PERSONAL_SANITARIO": 23,
76
+ "B-INSTITUCION": 25,
77
+ "B-NOMBRE_PERSONAL_SANITARIO": 27,
78
+ "B-NOMBRE_SUJETO_ASISTENCIA": 29,
79
+ "B-NUMERO_FAX": 31,
80
+ "B-NUMERO_TELEFONO": 33,
81
+ "B-OTROS_SUJETO_ASISTENCIA": 35,
82
+ "B-PAIS": 37,
83
+ "B-PROFESION": 39,
84
+ "B-SEXO_SUJETO_ASISTENCIA": 41,
85
+ "B-TERRITORIO": 43,
86
+ "I-CALLE": 2,
87
+ "I-CENTRO_SALUD": 4,
88
+ "I-CORREO_ELECTRONICO": 6,
89
+ "I-EDAD_SUJETO_ASISTENCIA": 8,
90
+ "I-FAMILIARES_SUJETO_ASISTENCIA": 10,
91
+ "I-FECHAS": 12,
92
+ "I-HOSPITAL": 14,
93
+ "I-ID_ASEGURAMIENTO": 16,
94
+ "I-ID_CONTACTO_ASISTENCIAL": 18,
95
+ "I-ID_EMPLEO_PERSONAL_SANITARIO": 20,
96
+ "I-ID_SUJETO_ASISTENCIA": 22,
97
+ "I-ID_TITULACION_PERSONAL_SANITARIO": 24,
98
+ "I-INSTITUCION": 26,
99
+ "I-NOMBRE_PERSONAL_SANITARIO": 28,
100
+ "I-NOMBRE_SUJETO_ASISTENCIA": 30,
101
+ "I-NUMERO_FAX": 32,
102
+ "I-NUMERO_TELEFONO": 34,
103
+ "I-OTROS_SUJETO_ASISTENCIA": 36,
104
+ "I-PAIS": 38,
105
+ "I-PROFESION": 40,
106
+ "I-SEXO_SUJETO_ASISTENCIA": 42,
107
+ "I-TERRITORIO": 44,
108
+ "O": 0
109
+ },
110
+ "layer_norm_eps": 1e-05,
111
+ "max_position_embeddings": 514,
112
+ "model_type": "roberta",
113
+ "num_attention_heads": 12,
114
+ "num_hidden_layers": 12,
115
+ "pad_token_id": 1,
116
+ "position_embedding_type": "absolute",
117
+ "torch_dtype": "float32",
118
+ "transformers_version": "4.30.1",
119
+ "type_vocab_size": 1,
120
+ "use_cache": true,
121
+ "vocab_size": 50262
122
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7deb486defe6391378a13324837513dd0b35a5188d32191842c6c739d28db560
3
+ size 496420401
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "max_len": 512,
38
+ "model_max_length": 512,
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73db2d2cf5dccb7e7791515fd1b17b839a0c8bdd8f23a2f99572bf58aa9b88ba
3
+ size 3887
vocab.json ADDED
The diff for this file is too large to render. See raw diff