Hugging Face's logo

anonymous13542
/
XLMR-large-metadata-council-en

Token Classification
Transformers
Safetensors
English
Portuguese
xlm-roberta
named-entity-recognition
metadata-extraction
bert
meeting-minutes
municipal-documents
Model card Files
xet
 Community
anonymous13542 commited on
Commit
c2352f4
·
verified ·
1 Parent(s): d454eca

Upload 6 files

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. config.json +85 -0
  3. model.safetensors +3 -0
  4. sentencepiece.bpe.model +3 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +3 -0
  7. tokenizer_config.json +55 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-DATA",
15
+ "2": "I-DATA",
16
+ "3": "B-HORARIO-INICIO",
17
+ "4": "I-HORARIO-INICIO",
18
+ "5": "B-HORARIO-FIM",
19
+ "6": "I-HORARIO-FIM",
20
+ "7": "B-LOCAL",
21
+ "8": "I-LOCAL",
22
+ "9": "B-TIPO-REUNIAO-EXTRAORDINARIA",
23
+ "10": "I-TIPO-REUNIAO-EXTRAORDINARIA",
24
+ "11": "B-TIPO-REUNIAO-ORDINARIA",
25
+ "12": "I-TIPO-REUNIAO-ORDINARIA",
26
+ "13": "B-NUMERO-ATA",
27
+ "14": "I-NUMERO-ATA",
28
+ "15": "B-PARTICIPANTE-PRESIDENTE-PRESENTE",
29
+ "16": "I-PARTICIPANTE-PRESIDENTE-PRESENTE",
30
+ "17": "B-PARTICIPANTE-PRESIDENTE-AUSENTE",
31
+ "18": "I-PARTICIPANTE-PRESIDENTE-AUSENTE",
32
+ "19": "B-PARTICIPANTE-PRESIDENTE-SUBSTITUIDO",
33
+ "20": "I-PARTICIPANTE-PRESIDENTE-SUBSTITUIDO",
34
+ "21": "B-PARTICIPANTE-VEREADOR-PRESENTE",
35
+ "22": "I-PARTICIPANTE-VEREADOR-PRESENTE",
36
+ "23": "B-PARTICIPANTE-VEREADOR-AUSENTE",
37
+ "24": "I-PARTICIPANTE-VEREADOR-AUSENTE",
38
+ "25": "B-PARTICIPANTE-VEREADOR-SUBSTITUIDO",
39
+ "26": "I-PARTICIPANTE-VEREADOR-SUBSTITUIDO"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 4096,
43
+ "label2id": {
44
+ "B-DATA": 1,
45
+ "B-HORARIO-FIM": 5,
46
+ "B-HORARIO-INICIO": 3,
47
+ "B-LOCAL": 7,
48
+ "B-NUMERO-ATA": 13,
49
+ "B-PARTICIPANTE-PRESIDENTE-AUSENTE": 17,
50
+ "B-PARTICIPANTE-PRESIDENTE-PRESENTE": 15,
51
+ "B-PARTICIPANTE-PRESIDENTE-SUBSTITUIDO": 19,
52
+ "B-PARTICIPANTE-VEREADOR-AUSENTE": 23,
53
+ "B-PARTICIPANTE-VEREADOR-PRESENTE": 21,
54
+ "B-PARTICIPANTE-VEREADOR-SUBSTITUIDO": 25,
55
+ "B-TIPO-REUNIAO-EXTRAORDINARIA": 9,
56
+ "B-TIPO-REUNIAO-ORDINARIA": 11,
57
+ "I-DATA": 2,
58
+ "I-HORARIO-FIM": 6,
59
+ "I-HORARIO-INICIO": 4,
60
+ "I-LOCAL": 8,
61
+ "I-NUMERO-ATA": 14,
62
+ "I-PARTICIPANTE-PRESIDENTE-AUSENTE": 18,
63
+ "I-PARTICIPANTE-PRESIDENTE-PRESENTE": 16,
64
+ "I-PARTICIPANTE-PRESIDENTE-SUBSTITUIDO": 20,
65
+ "I-PARTICIPANTE-VEREADOR-AUSENTE": 24,
66
+ "I-PARTICIPANTE-VEREADOR-PRESENTE": 22,
67
+ "I-PARTICIPANTE-VEREADOR-SUBSTITUIDO": 26,
68
+ "I-TIPO-REUNIAO-EXTRAORDINARIA": 10,
69
+ "I-TIPO-REUNIAO-ORDINARIA": 12,
70
+ "O": 0
71
+ },
72
+ "layer_norm_eps": 1e-05,
73
+ "max_position_embeddings": 514,
74
+ "model_type": "xlm-roberta",
75
+ "num_attention_heads": 16,
76
+ "num_hidden_layers": 24,
77
+ "output_past": true,
78
+ "pad_token_id": 1,
79
+ "position_embedding_type": "absolute",
80
+ "torch_dtype": "float32",
81
+ "transformers_version": "4.54.0",
82
+ "type_vocab_size": 1,
83
+ "use_cache": true,
84
+ "vocab_size": 250002
85
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1960e3ffa1fdf6109f97496485b04960ce6589d2486ca0198d9c41f1f4df1878
3
+ size 2235522564
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
3
+ size 17082734
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }