Upload ./ with huggingface_hub

#1
by Ertugrul - opened
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dbmdz/bert-base-turkish-128k-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "Lojistik",
13
+ "1": "Elektrik Kaynagi",
14
+ "2": "Arama Ekipmani",
15
+ "3": "Cenaze",
16
+ "4": "Giysi",
17
+ "5": "Enkaz Kaldirma",
18
+ "6": "Isinma",
19
+ "7": "Bar\u0131nma",
20
+ "8": "Tuvalet",
21
+ "9": "Su",
22
+ "10": "Yemek",
23
+ "11": "Saglik",
24
+ "12": "Alakasiz"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "Alakasiz": 12,
30
+ "Arama Ekipmani": 2,
31
+ "Bar\u0131nma": 7,
32
+ "Cenaze": 3,
33
+ "Elektrik Kaynagi": 1,
34
+ "Enkaz Kaldirma": 5,
35
+ "Giysi": 4,
36
+ "Isinma": 6,
37
+ "Lojistik": 0,
38
+ "Saglik": 11,
39
+ "Su": 9,
40
+ "Tuvalet": 8,
41
+ "Yemek": 10
42
+ },
43
+ "layer_norm_eps": 1e-12,
44
+ "max_position_embeddings": 512,
45
+ "model_type": "bert",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 12,
48
+ "pad_token_id": 0,
49
+ "position_embedding_type": "absolute",
50
+ "problem_type": "multi_label_classification",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.24.0",
53
+ "type_vocab_size": 2,
54
+ "use_cache": true,
55
+ "vocab_size": 128000
56
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd471f76d2248215dddc2d39ffa6789c4c7e91ad50bad91e909d500737d038e
3
+ size 737494133
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "max_len": 512,
7
+ "name_or_path": "dbmdz/bert-base-turkish-128k-uncased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c609d725641bfec802236074012104ac3fb3a714d45eb1fd3beacbdedbe54c8d
3
+ size 3451
vocab.txt ADDED
The diff for this file is too large to render. See raw diff