Emanuel commited on
Commit
76241cb
1 Parent(s): 7d337b3

First commit

Browse files
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "neuralmind/bert-base-portuguese-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "pos",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "ADJ",
15
+ "1": "ADP",
16
+ "2": "ADV",
17
+ "3": "AUX",
18
+ "4": "CCONJ",
19
+ "5": "DET",
20
+ "6": "INTJ",
21
+ "7": "NOUN",
22
+ "8": "NUM",
23
+ "9": "PRON",
24
+ "10": "PROPN",
25
+ "11": "PUNCT",
26
+ "12": "SCONJ",
27
+ "13": "SYM",
28
+ "14": "VERB",
29
+ "15": "X"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "label2id": {
34
+ "ADJ": 0,
35
+ "ADP": 1,
36
+ "ADV": 2,
37
+ "AUX": 3,
38
+ "CCONJ": 4,
39
+ "DET": 5,
40
+ "INTJ": 6,
41
+ "NOUN": 7,
42
+ "NUM": 8,
43
+ "PRON": 9,
44
+ "PROPN": 10,
45
+ "PUNCT": 11,
46
+ "SCONJ": 12,
47
+ "SYM": 13,
48
+ "VERB": 14,
49
+ "X": 15
50
+ },
51
+ "layer_norm_eps": 1e-12,
52
+ "max_position_embeddings": 512,
53
+ "model_type": "bert",
54
+ "num_attention_heads": 12,
55
+ "num_hidden_layers": 12,
56
+ "output_past": true,
57
+ "pad_token_id": 0,
58
+ "pooler_fc_size": 768,
59
+ "pooler_num_attention_heads": 12,
60
+ "pooler_num_fc_layers": 3,
61
+ "pooler_size_per_head": 128,
62
+ "pooler_type": "first_token_transform",
63
+ "position_embedding_type": "absolute",
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.23.1",
66
+ "type_vocab_size": 2,
67
+ "use_cache": true,
68
+ "vocab_size": 29794
69
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb9d7d5b63f823da1f137264ce155f71ee237e87398e865d82be6f5a93a58fb
3
+ size 433449777
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "name_or_path": "neuralmind/bert-base-portuguese-cased",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43596163eaeea5899eb72d56d29c49009826bc7788d4a9dfc11cf95e53c36d7c
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff