Sarpyy commited on
Commit
6c213e9
·
verified ·
1 Parent(s): 4841984

Initial_Commit

Browse files

We fixed, date, time and some punctuation problems in the model.

Files changed (4) hide show
  1. config.json +60 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +15 -0
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.2,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.2,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "AD-NOUN",
16
+ "1": "ADIL-PRONOUN",
17
+ "2": "BA\u011eLA\u00c7-CONJUCTION",
18
+ "3": "BA\u011eLA\u00c7-CONJUNCTION",
19
+ "4": "BEL\u0130RLEY\u0130C\u0130-DETERMINER",
20
+ "5": "BEL\u0130RTE\u00c7-ADVERB",
21
+ "6": "F\u0130\u0130L-VERB",
22
+ "7": "NOKTALAMA-PUNCTUATION",
23
+ "8": "SAYI-NUMBER",
24
+ "9": "SIFAT-ADJECTIVE",
25
+ "10": "SORU-QUESTION",
26
+ "11": "TAR\u0130H-DATE",
27
+ "12": "ZARF-ADVERB",
28
+ "13": "\u0130LGE\u00c7-PREPOSITION"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "is_decoder": false,
33
+ "label2id": {
34
+ "AD-NOUN": 0,
35
+ "ADIL-PRONOUN": 1,
36
+ "BA\u011eLA\u00c7-CONJUCTION": 2,
37
+ "BA\u011eLA\u00c7-CONJUNCTION": 3,
38
+ "BEL\u0130RLEY\u0130C\u0130-DETERMINER": 4,
39
+ "BEL\u0130RTE\u00c7-ADVERB": 5,
40
+ "F\u0130\u0130L-VERB": 6,
41
+ "NOKTALAMA-PUNCTUATION": 7,
42
+ "SAYI-NUMBER": 8,
43
+ "SIFAT-ADJECTIVE": 9,
44
+ "SORU-QUESTION": 10,
45
+ "TAR\u0130H-DATE": 11,
46
+ "ZARF-ADVERB": 12,
47
+ "\u0130LGE\u00c7-PREPOSITION": 13
48
+ },
49
+ "layer_norm_eps": 1e-12,
50
+ "max_position_embeddings": 512,
51
+ "model_type": "bert",
52
+ "num_attention_heads": 12,
53
+ "num_hidden_layers": 12,
54
+ "pad_token_id": 0,
55
+ "tie_word_embeddings": true,
56
+ "transformers_version": "5.1.0",
57
+ "type_vocab_size": 2,
58
+ "use_cache": false,
59
+ "vocab_size": 32000
60
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3f068b46c4a7563c56997c691e3ff2b13bb6aed5e8273f4cd8bc8aa1540e79
3
+ size 440173400
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "max_len": 512,
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }