Hugging Face's logo

girayyagmur
/
bert-base-turkish-ner-cased

Token Classification
Transformers
Safetensors
Turkish
bert
chemistry
music
finance
ner
turkish
Inference Endpoints
Model card Files Community
girayyagmur commited on
Commit
2ffe933
·
verified ·
1 Parent(s): 9e754b7

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +108 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer_config.json +58 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "akdeniz27/bert-base-turkish-cased-ner",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-PERSON",
15
+ "2": "B-ORDINAL",
16
+ "3": "B-GPE",
17
+ "4": "B-CARDINAL",
18
+ "5": "B-DATE",
19
+ "6": "I-DATE",
20
+ "7": "B-EVENT",
21
+ "8": "I-EVENT",
22
+ "9": "B-FAC",
23
+ "10": "I-FAC",
24
+ "11": "I-GPE",
25
+ "12": "I-PERSON",
26
+ "13": "B-LANGUAGE",
27
+ "14": "B-TITLE",
28
+ "15": "B-ORG",
29
+ "16": "I-ORG",
30
+ "17": "I-TITLE",
31
+ "18": "B-LOC",
32
+ "19": "I-LOC",
33
+ "20": "B-NORP",
34
+ "21": "I-NORP",
35
+ "22": "B-QUANTITY",
36
+ "23": "I-QUANTITY",
37
+ "24": "B-WORK_OF_ART",
38
+ "25": "I-WORK_OF_ART",
39
+ "26": "I-CARDINAL",
40
+ "27": "B-PERCENT",
41
+ "28": "I-PERCENT",
42
+ "29": "B-PRODUCT",
43
+ "30": "I-ORDINAL",
44
+ "31": "B-MONEY",
45
+ "32": "I-MONEY",
46
+ "33": "I-LANGUAGE",
47
+ "34": "I-PRODUCT",
48
+ "35": "B-TIME",
49
+ "36": "B-LAW",
50
+ "37": "I-LAW",
51
+ "38": "I-TIME"
52
+ },
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": 3072,
55
+ "label2id": {
56
+ "B-CARDINAL": 4,
57
+ "B-DATE": 5,
58
+ "B-EVENT": 7,
59
+ "B-FAC": 9,
60
+ "B-GPE": 3,
61
+ "B-LANGUAGE": 13,
62
+ "B-LAW": 36,
63
+ "B-LOC": 18,
64
+ "B-MONEY": 31,
65
+ "B-NORP": 20,
66
+ "B-ORDINAL": 2,
67
+ "B-ORG": 15,
68
+ "B-PERCENT": 27,
69
+ "B-PERSON": 1,
70
+ "B-PRODUCT": 29,
71
+ "B-QUANTITY": 22,
72
+ "B-TIME": 35,
73
+ "B-TITLE": 14,
74
+ "B-WORK_OF_ART": 24,
75
+ "I-CARDINAL": 26,
76
+ "I-DATE": 6,
77
+ "I-EVENT": 8,
78
+ "I-FAC": 10,
79
+ "I-GPE": 11,
80
+ "I-LANGUAGE": 33,
81
+ "I-LAW": 37,
82
+ "I-LOC": 19,
83
+ "I-MONEY": 32,
84
+ "I-NORP": 21,
85
+ "I-ORDINAL": 30,
86
+ "I-ORG": 16,
87
+ "I-PERCENT": 28,
88
+ "I-PERSON": 12,
89
+ "I-PRODUCT": 34,
90
+ "I-QUANTITY": 23,
91
+ "I-TIME": 38,
92
+ "I-TITLE": 17,
93
+ "I-WORK_OF_ART": 25,
94
+ "O": 0
95
+ },
96
+ "layer_norm_eps": 1e-12,
97
+ "max_position_embeddings": 512,
98
+ "model_type": "bert",
99
+ "num_attention_heads": 12,
100
+ "num_hidden_layers": 12,
101
+ "pad_token_id": 0,
102
+ "position_embedding_type": "absolute",
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.36.2",
105
+ "type_vocab_size": 2,
106
+ "use_cache": true,
107
+ "vocab_size": 32000
108
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:469113ad81a3aa9ccbf64a6f74691008191aea308ca3cd1eccf49c194e308e3f
3
+ size 440250324
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff