Mustafa Öztürk commited on
Commit
4edfd3b
·
1 Parent(s): 5bdeec3

Add offensive model files for HF runtime

Browse files
.gitignore CHANGED
@@ -46,7 +46,6 @@ Thumbs.db
46
  *.pid
47
 
48
  # Local model caches / weights
49
- models_cache/
50
 
51
  # Streamlit local state
52
  .streamlit/secrets.toml
 
46
  *.pid
47
 
48
  # Local model caches / weights
 
49
 
50
  # Streamlit local state
51
  .streamlit/secrets.toml
models_cache/bertturk-offensive-42k/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
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": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "is_decoder": false,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "bert",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "pad_token_id": 0,
23
+ "problem_type": "single_label_classification",
24
+ "tie_word_embeddings": true,
25
+ "transformers_version": "5.0.0",
26
+ "type_vocab_size": 2,
27
+ "use_cache": false,
28
+ "vocab_size": 32000
29
+ }
models_cache/bertturk-offensive-42k/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:909f70e7087ade4a12d6ede9a19c4e0d4083617854e4552ee9773ab1664cc3c2
3
+ size 442499040
models_cache/bertturk-offensive-42k/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models_cache/bertturk-offensive-42k/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
+ }