colinswaelens commited on
Commit
b32ab1a
·
verified ·
1 Parent(s): ff9cb41

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "colinswaelens/DBBErt",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1,
32
+ "LABEL_10": 10,
33
+ "LABEL_11": 11,
34
+ "LABEL_12": 12,
35
+ "LABEL_13": 13,
36
+ "LABEL_2": 2,
37
+ "LABEL_3": 3,
38
+ "LABEL_4": 4,
39
+ "LABEL_5": 5,
40
+ "LABEL_6": 6,
41
+ "LABEL_7": 7,
42
+ "LABEL_8": 8,
43
+ "LABEL_9": 9
44
+ },
45
+ "layer_norm_eps": 1e-12,
46
+ "max_position_embeddings": 512,
47
+ "model_type": "bert",
48
+ "num_attention_heads": 12,
49
+ "num_hidden_layers": 12,
50
+ "pad_token_id": 0,
51
+ "position_embedding_type": "absolute",
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.20.0",
54
+ "type_vocab_size": 2,
55
+ "use_cache": true,
56
+ "vocab_size": 30522
57
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ad1467ee7be9c2dff335a9c327f5aa344520029ebdcf7a193dbb6603137828
3
+ size 435682218
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": true,
4
+ "mask_token": "[MASK]",
5
+ "max_length": 512,
6
+ "name_or_path": "colinswaelens/DBBErt",
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d531f3a69c8e7921c6f476f7af3d63d935417210c58becf14eedbf04d9dcc4d2
3
+ size 3832
vocab.txt ADDED
The diff for this file is too large to render. See raw diff