uygarkurt commited on
Commit
b4d452e
1 Parent(s): bae8203

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dbmdz/electra-base-turkish-cased-discriminator",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "ElectraForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "embedding_size": 768,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "PERIOD",
16
+ "2": "COMMA",
17
+ "3": "QUESTION_MARK"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "COMMA": 2,
23
+ "O": 0,
24
+ "PERIOD": 1,
25
+ "QUESTION_MARK": 3
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "electra",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "output_past": true,
33
+ "pad_token_id": 0,
34
+ "position_embedding_type": "absolute",
35
+ "summary_activation": "gelu",
36
+ "summary_last_dropout": 0.1,
37
+ "summary_type": "first",
38
+ "summary_use_proj": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.25.1",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 32000
44
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454e0dc382548b077b47ac83620f24c9dbc34ae88a567fa9e9061cd9ab544e60
3
+ size 440192045
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 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "max_len": 512,
7
+ "model_max_length": 512,
8
+ "name_or_path": "dbmdz/electra-base-turkish-cased-discriminator",
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "special_tokens_map_file": null,
13
+ "strip_accents": false,
14
+ "tokenize_chinese_chars": true,
15
+ "tokenizer_class": "ElectraTokenizer",
16
+ "unk_token": "[UNK]"
17
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff