Update model version
Browse files- config.json +71 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "PART",
|
24 |
+
"10": "PRON",
|
25 |
+
"11": "PROPN",
|
26 |
+
"12": "PUNCT",
|
27 |
+
"13": "SCONJ",
|
28 |
+
"14": "SYM",
|
29 |
+
"15": "VERB",
|
30 |
+
"16": "X"
|
31 |
+
},
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"intermediate_size": 3072,
|
34 |
+
"label2id": {
|
35 |
+
"ADJ": 0,
|
36 |
+
"ADP": 1,
|
37 |
+
"ADV": 2,
|
38 |
+
"AUX": 3,
|
39 |
+
"CCONJ": 4,
|
40 |
+
"DET": 5,
|
41 |
+
"INTJ": 6,
|
42 |
+
"NOUN": 7,
|
43 |
+
"NUM": 8,
|
44 |
+
"PART": 9,
|
45 |
+
"PRON": 10,
|
46 |
+
"PROPN": 11,
|
47 |
+
"PUNCT": 12,
|
48 |
+
"SCONJ": 13,
|
49 |
+
"SYM": 14,
|
50 |
+
"VERB": 15,
|
51 |
+
"X": 16
|
52 |
+
},
|
53 |
+
"layer_norm_eps": 1e-12,
|
54 |
+
"max_position_embeddings": 512,
|
55 |
+
"model_type": "bert",
|
56 |
+
"num_attention_heads": 12,
|
57 |
+
"num_hidden_layers": 12,
|
58 |
+
"output_past": true,
|
59 |
+
"pad_token_id": 0,
|
60 |
+
"pooler_fc_size": 768,
|
61 |
+
"pooler_num_attention_heads": 12,
|
62 |
+
"pooler_num_fc_layers": 3,
|
63 |
+
"pooler_size_per_head": 128,
|
64 |
+
"pooler_type": "first_token_transform",
|
65 |
+
"position_embedding_type": "absolute",
|
66 |
+
"torch_dtype": "float32",
|
67 |
+
"transformers_version": "4.24.0",
|
68 |
+
"type_vocab_size": 2,
|
69 |
+
"use_cache": true,
|
70 |
+
"vocab_size": 29794
|
71 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb1c0c0489bdb4b55b305ca02e0cba1aa06164c8edae3a966f363c99676a0279
|
3 |
+
size 433452913
|
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:b6a66ea0e0fb362abc4f707b50c3c822c460db6bd106f2563c02a792fa76cff7
|
3 |
+
size 3439
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|