Hugging Face's logo

VOCALINLP
/
spanish_capitalization_punctuation_restoration_sanivert

Token Classification
Transformers
Safetensors
Spanish
bert
Inference Endpoints
Model card Files Community
jcg00v commited on
Commit
b557811
•
1 Parent(s): 12b3f46

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +67 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +57 -0
  6. training_args.bin +3 -0
  7. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "l",
14
+ "1": "u",
15
+ "2": "¿u",
16
+ "3": "¿l",
17
+ "4": "?u",
18
+ "5": "?l",
19
+ "6": "¡l",
20
+ "7": "¡u",
21
+ "8": "!u",
22
+ "9": "!l",
23
+ "10": ",u",
24
+ "11": ",l",
25
+ "12": ".u",
26
+ "13": ".l",
27
+ "14": ":u",
28
+ "15": ":l",
29
+ "16": "¿?u",
30
+ "17": "¡!u"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
+ "label2id": {
35
+ "l": 0,
36
+ "u": 1,
37
+ ",u": 10,
38
+ ",l": 11,
39
+ ".u": 12,
40
+ ".l": 13,
41
+ ":u": 14,
42
+ ":l": 15,
43
+ "¿?u": 16,
44
+ "¡!u": 17,
45
+ "¿u": 2,
46
+ "¿l": 3,
47
+ "?u": 4,
48
+ "?l": 5,
49
+ "¡l": 6,
50
+ "¡u": 7,
51
+ "!u": 8,
52
+ "!l": 9
53
+ },
54
+ "layer_norm_eps": 1e-12,
55
+ "max_position_embeddings": 512,
56
+ "model_type": "bert",
57
+ "num_attention_heads": 12,
58
+ "num_hidden_layers": 12,
59
+ "output_past": true,
60
+ "pad_token_id": 1,
61
+ "position_embedding_type": "absolute",
62
+ "torch_dtype": "float32",
63
+ "transformers_version": "4.37.0.dev0",
64
+ "type_vocab_size": 2,
65
+ "use_cache": true,
66
+ "vocab_size": 31002
67
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7844ab3e55717def8dfb144aaa158bf512a7d027a61500b1833cc92ee1cc0db4
3
+ size 437119864
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[MASK]",
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
+ "3": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "[SEP]",
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": false,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f5b6e5d8cd7ed2dad2cdcbe3f876b1694e0fc8cd31257ba37e75ec51e6eb34
3
+ size 4664
vocab.txt ADDED
The diff for this file is too large to render. See raw diff