uygarkurt commited on
Commit
a0e89fd
1 Parent(s): 00ba008

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dbmdz/convbert-base-turkish-cased",
3
+ "architectures": [
4
+ "ConvBertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "conv_kernel_size": 9,
10
+ "embedding_size": 768,
11
+ "eos_token_id": 2,
12
+ "head_ratio": 2,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "O",
18
+ "1": "PERIOD",
19
+ "2": "COMMA",
20
+ "3": "QUESTION_MARK"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "COMMA": 2,
26
+ "O": 0,
27
+ "PERIOD": 1,
28
+ "QUESTION_MARK": 3
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "convbert",
33
+ "num_attention_heads": 12,
34
+ "num_groups": 1,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.25.1",
39
+ "type_vocab_size": 2,
40
+ "vocab_size": 32000
41
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3b56e7faa87b9aa5acfe1af841557eb3d410658ab453c1f9e8c4b4d76e11b82
3
+ size 427378109
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/convbert-base-turkish-cased",
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": "ConvBertTokenizer",
16
+ "unk_token": "[UNK]"
17
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff