marcosgg commited on
Commit
68f34a5
1 Parent(s): aa2ef2b

First commit

Browse files
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "neuralmind/bert-large-portuguese-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "ner",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "B-LOC",
15
+ "1": "B-MISC",
16
+ "2": "B-ORG",
17
+ "3": "B-PER",
18
+ "4": "I-LOC",
19
+ "5": "I-MISC",
20
+ "6": "I-ORG",
21
+ "7": "I-PER",
22
+ "8": "O"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 4096,
26
+ "label2id": {
27
+ "B-LOC": 0,
28
+ "B-MISC": 1,
29
+ "B-ORG": 2,
30
+ "B-PER": 3,
31
+ "I-LOC": 4,
32
+ "I-MISC": 5,
33
+ "I-ORG": 6,
34
+ "I-PER": 7,
35
+ "O": 8
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 16,
41
+ "num_hidden_layers": 24,
42
+ "output_past": true,
43
+ "pad_token_id": 0,
44
+ "pooler_fc_size": 768,
45
+ "pooler_num_attention_heads": 12,
46
+ "pooler_num_fc_layers": 3,
47
+ "pooler_size_per_head": 128,
48
+ "pooler_type": "first_token_transform",
49
+ "position_embedding_type": "absolute",
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.24.0",
52
+ "type_vocab_size": 2,
53
+ "use_cache": true,
54
+ "vocab_size": 29794
55
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b7526807502fcdf7829a64b31d239ec7648d885ceb087c171d5bcd0725767b
3
+ size 1333559473
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
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-large-portuguese-cased",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": "special_tokens_map.json",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff