akdeniz27 commited on
Commit
817b277
1 Parent(s): 720c502

First model version

Browse files
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "B-PER",
19
+ "2": "I-PER",
20
+ "3": "B-ORG",
21
+ "4": "I-ORG",
22
+ "5": "B-LOC",
23
+ "6": "I-LOC"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "O": 0,
29
+ "B-PER": 1,
30
+ "I-PER": 2,
31
+ "B-ORG": 3,
32
+ "I-ORG": 4,
33
+ "B-LOC": 5,
34
+ "I-LOC": 6
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "convbert",
39
+ "num_attention_heads": 12,
40
+ "num_groups": 1,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.10.2",
45
+ "type_vocab_size": 2,
46
+ "vocab_size": 32000
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3611da4e14bd64057a4e4a46916bbaf307f628baa5e71a210f26e079b79f0454
3
+ size 427404937
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "dbmdz/convbert-base-turkish-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_file": null, "tokenizer_class": "ConvBertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff