Hugging Face's logo

BSC-NLP4BIA
/
location-tagger

Token Classification
PyTorch
Spanish
roberta
NER
named entity recognition
biomedical
clinical
EHR
spanish
location
geopolitical
facility
geographical
transport
community
language
clinical department
Eval Results
Model card Files Community
janrodriguez commited on
Commit
e9644ea
•
1 Parent(s): a655506

Initial commit

Browse files
Files changed (8) hide show
  1. config.json +74 -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 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.1,
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-COMUNIDAD",
17
+ "2": "I-COMUNIDAD",
18
+ "3": "B-DEPARTAMENTO",
19
+ "4": "I-DEPARTAMENTO",
20
+ "5": "B-FAC_GEN",
21
+ "6": "I-FAC_GEN",
22
+ "7": "B-FAC_NOM",
23
+ "8": "I-FAC_NOM",
24
+ "9": "B-GEO_GEN",
25
+ "10": "I-GEO_GEN",
26
+ "11": "B-GEO_NOM",
27
+ "12": "I-GEO_NOM",
28
+ "13": "B-GPE_GEN",
29
+ "14": "I-GPE_GEN",
30
+ "15": "B-GPE_NOM",
31
+ "16": "I-GPE_NOM",
32
+ "17": "B-IDIOMA",
33
+ "18": "I-IDIOMA",
34
+ "19": "B-TRANSPORTE",
35
+ "20": "I-TRANSPORTE"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "label2id": {
40
+ "B-COMUNIDAD": 1,
41
+ "B-DEPARTAMENTO": 3,
42
+ "B-FAC_GEN": 5,
43
+ "B-FAC_NOM": 7,
44
+ "B-GEO_GEN": 9,
45
+ "B-GEO_NOM": 11,
46
+ "B-GPE_GEN": 13,
47
+ "B-GPE_NOM": 15,
48
+ "B-IDIOMA": 17,
49
+ "B-TRANSPORTE": 19,
50
+ "I-COMUNIDAD": 2,
51
+ "I-DEPARTAMENTO": 4,
52
+ "I-FAC_GEN": 6,
53
+ "I-FAC_NOM": 8,
54
+ "I-GEO_GEN": 10,
55
+ "I-GEO_NOM": 12,
56
+ "I-GPE_GEN": 14,
57
+ "I-GPE_NOM": 16,
58
+ "I-IDIOMA": 18,
59
+ "I-TRANSPORTE": 20,
60
+ "O": 0
61
+ },
62
+ "layer_norm_eps": 1e-05,
63
+ "max_position_embeddings": 514,
64
+ "model_type": "roberta",
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 12,
67
+ "pad_token_id": 1,
68
+ "position_embedding_type": "absolute",
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.30.2",
71
+ "type_vocab_size": 1,
72
+ "use_cache": true,
73
+ "vocab_size": 50262
74
+ }
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 sha256:3eeb5074a54e4d2da9f0899afbe433f116bcd84a4a5292d716d6e884264563e2
3
+ size 496346609
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 sha256:2aa43bf6c79fc877c579fd133872df66ebbfa01463556e1248bcf55db7e5ad7c
3
+ size 3951
vocab.json ADDED
The diff for this file is too large to render. See raw diff