fc63 commited on
Commit
b49e367
·
verified ·
1 Parent(s): 1a2ddbf

Updated fine-tuned toxic classification model.

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "dbmdz/bert-base-turkish-cased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "fc63/toxic-classification-model",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b85531c7ec26efd0ec87b5aaac09f768d9b4455bd3c8320a36ae35e401b87b5b
3
  size 442499064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e457cae89636c3d49b984b09f092953efc27e63b0de03935bf1b3697861eb77
3
  size 442499064
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
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 CHANGED
@@ -48,12 +48,19 @@
48
  "extra_special_tokens": {},
49
  "mask_token": "[MASK]",
50
  "max_len": 512,
 
51
  "model_max_length": 512,
52
  "never_split": null,
 
53
  "pad_token": "[PAD]",
 
 
54
  "sep_token": "[SEP]",
 
55
  "strip_accents": null,
56
  "tokenize_chinese_chars": true,
57
  "tokenizer_class": "BertTokenizer",
 
 
58
  "unk_token": "[UNK]"
59
  }
 
48
  "extra_special_tokens": {},
49
  "mask_token": "[MASK]",
50
  "max_len": 512,
51
+ "max_length": 128,
52
  "model_max_length": 512,
53
  "never_split": null,
54
+ "pad_to_multiple_of": null,
55
  "pad_token": "[PAD]",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
  "sep_token": "[SEP]",
59
+ "stride": 0,
60
  "strip_accents": null,
61
  "tokenize_chinese_chars": true,
62
  "tokenizer_class": "BertTokenizer",
63
+ "truncation_side": "right",
64
+ "truncation_strategy": "longest_first",
65
  "unk_token": "[UNK]"
66
  }