erickrribeiro
commited on
Commit
•
115aa23
1
Parent(s):
097088d
Training in progress, epoch 1
Browse files- config.json +94 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-APLICATIVO",
|
15 |
+
"2": "I-APLICATIVO",
|
16 |
+
"3": "B-ATENDIMENTO",
|
17 |
+
"4": "I-ATENDIMENTO",
|
18 |
+
"5": "B-AUDIO",
|
19 |
+
"6": "I-AUDIO",
|
20 |
+
"7": "B-BATERIA",
|
21 |
+
"8": "I-BATERIA",
|
22 |
+
"9": "B-CONEX\u00c3O",
|
23 |
+
"10": "I-CONEX\u00c3O",
|
24 |
+
"11": "B-DESEMPENHO",
|
25 |
+
"12": "I-DESEMPENHO",
|
26 |
+
"13": "B-DESIGN",
|
27 |
+
"14": "I-DESIGN",
|
28 |
+
"15": "B-HARDWARE",
|
29 |
+
"16": "I-HARDWARE",
|
30 |
+
"17": "B-MARCA",
|
31 |
+
"18": "I-MARCA",
|
32 |
+
"19": "B-MEMORIA",
|
33 |
+
"20": "I-MEMORIA",
|
34 |
+
"21": "B-PRE\u00c7O",
|
35 |
+
"22": "I-PRE\u00c7O",
|
36 |
+
"23": "B-SISTEMA",
|
37 |
+
"24": "I-SISTEMA",
|
38 |
+
"25": "B-TECLADO",
|
39 |
+
"26": "I-TECLADO",
|
40 |
+
"27": "B-TELA",
|
41 |
+
"28": "I-TELA"
|
42 |
+
},
|
43 |
+
"initializer_range": 0.02,
|
44 |
+
"intermediate_size": 3072,
|
45 |
+
"label2id": {
|
46 |
+
"B-APLICATIVO": 1,
|
47 |
+
"B-ATENDIMENTO": 3,
|
48 |
+
"B-AUDIO": 5,
|
49 |
+
"B-BATERIA": 7,
|
50 |
+
"B-CONEX\u00c3O": 9,
|
51 |
+
"B-DESEMPENHO": 11,
|
52 |
+
"B-DESIGN": 13,
|
53 |
+
"B-HARDWARE": 15,
|
54 |
+
"B-MARCA": 17,
|
55 |
+
"B-MEMORIA": 19,
|
56 |
+
"B-PRE\u00c7O": 21,
|
57 |
+
"B-SISTEMA": 23,
|
58 |
+
"B-TECLADO": 25,
|
59 |
+
"B-TELA": 27,
|
60 |
+
"I-APLICATIVO": 2,
|
61 |
+
"I-ATENDIMENTO": 4,
|
62 |
+
"I-AUDIO": 6,
|
63 |
+
"I-BATERIA": 8,
|
64 |
+
"I-CONEX\u00c3O": 10,
|
65 |
+
"I-DESEMPENHO": 12,
|
66 |
+
"I-DESIGN": 14,
|
67 |
+
"I-HARDWARE": 16,
|
68 |
+
"I-MARCA": 18,
|
69 |
+
"I-MEMORIA": 20,
|
70 |
+
"I-PRE\u00c7O": 22,
|
71 |
+
"I-SISTEMA": 24,
|
72 |
+
"I-TECLADO": 26,
|
73 |
+
"I-TELA": 28,
|
74 |
+
"O": 0
|
75 |
+
},
|
76 |
+
"layer_norm_eps": 1e-12,
|
77 |
+
"max_position_embeddings": 512,
|
78 |
+
"model_type": "bert",
|
79 |
+
"num_attention_heads": 12,
|
80 |
+
"num_hidden_layers": 12,
|
81 |
+
"output_past": true,
|
82 |
+
"pad_token_id": 0,
|
83 |
+
"pooler_fc_size": 768,
|
84 |
+
"pooler_num_attention_heads": 12,
|
85 |
+
"pooler_num_fc_layers": 3,
|
86 |
+
"pooler_size_per_head": 128,
|
87 |
+
"pooler_type": "first_token_transform",
|
88 |
+
"position_embedding_type": "absolute",
|
89 |
+
"torch_dtype": "float32",
|
90 |
+
"transformers_version": "4.36.0",
|
91 |
+
"type_vocab_size": 2,
|
92 |
+
"use_cache": true,
|
93 |
+
"vocab_size": 29794
|
94 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25ab6d56dc81adb85e51a4dd72bf57840d341c406c0445bffde583f5ea0c673b
|
3 |
+
size 433442724
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
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": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
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 sha256:4a5f6eb5d22eb594c0e4410c22222b740fa0cd949336a79b0a0323cdc18978ed
|
3 |
+
size 4219
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|