IvanFed commited on
Commit
abf0a81
·
verified ·
1 Parent(s): 75547fe

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +10 -0
  2. pytorch_model.bin +3 -0
  3. thresholds.json +5 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +24 -0
config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "cointegrated/rubert-tiny2",
3
+ "hidden_size": 312,
4
+ "num_classes": 3,
5
+ "class_names": [
6
+ "profanity",
7
+ "threat",
8
+ "illegal"
9
+ ]
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a0b0234d72a459ac322437665e6f8af44294de3b369ca15f027b7a87bd1212
3
+ size 116802430
thresholds.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "Profanity": 0.45,
3
+ "Threat": 0.35,
4
+ "Illegal": 0.5
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "is_local": false,
7
+ "local_files_only": false,
8
+ "mask_token": "[MASK]",
9
+ "max_length": 512,
10
+ "model_max_length": 2048,
11
+ "never_split": null,
12
+ "pad_to_multiple_of": null,
13
+ "pad_token": "[PAD]",
14
+ "pad_token_type_id": 0,
15
+ "padding_side": "right",
16
+ "sep_token": "[SEP]",
17
+ "stride": 0,
18
+ "strip_accents": null,
19
+ "tokenize_chinese_chars": true,
20
+ "tokenizer_class": "BertTokenizer",
21
+ "truncation_side": "right",
22
+ "truncation_strategy": "longest_first",
23
+ "unk_token": "[UNK]"
24
+ }