p208p2002 commited on
Commit
8d6b106
β€’
1 Parent(s): a6108a2

Upload 7 files

Browse files
README.md ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ # zh-wiki-punctuation-restore
2
+ More Detail: https://github.com/p208p2002/ZH-Punctuation-Restore
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-chinese",
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": "S-\uff0c",
15
+ "2": "S-\u3001",
16
+ "3": "S-\u3002",
17
+ "4": "S-\uff1f",
18
+ "5": "S-\uff01",
19
+ "6": "S-\uff1b"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "O": 0,
25
+ "S-\u3001": 2,
26
+ "S-\u3002": 3,
27
+ "S-\uff01": 5,
28
+ "S-\uff0c": 1,
29
+ "S-\uff1b": 6,
30
+ "S-\uff1f": 4
31
+ },
32
+ "layer_norm_eps": 1e-12,
33
+ "max_position_embeddings": 512,
34
+ "model_type": "bert",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "pad_token_id": 0,
38
+ "pooler_fc_size": 768,
39
+ "pooler_num_attention_heads": 12,
40
+ "pooler_num_fc_layers": 3,
41
+ "pooler_size_per_head": 128,
42
+ "pooler_type": "first_token_transform",
43
+ "position_embedding_type": "absolute",
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.25.1",
46
+ "type_vocab_size": 2,
47
+ "use_cache": true,
48
+ "vocab_size": 21128
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f7c16f858cac9abd5b02207be197ff81159c77f059fba192073f149350b421
3
+ size 406799085
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-base-chinese",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff