nassga commited on
Commit
ba5a867
·
1 Parent(s): ca9faf9

/content/Arabic-Offensive-Multi-Platform-SocialMedia-Comment-Dataset/data/drive/MyDrive/PFE/arabic-cyberbulling-model

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aubmindlab/bert-base-arabertv02-twitter",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "Offensive",
14
+ "1": "Non-Offensive"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "Non-Offensive": 1,
20
+ "Offensive": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.28.0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 64000
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c83d0d9dfe519cd0630b6cba5a5da5cf23de3cfc42a6675166ea22ae69270334
3
+ size 540852341
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "max_len": 512,
8
+ "model_max_length": 512,
9
+ "never_split": [
10
+ "[بريد]",
11
+ "[مستخدم]",
12
+ "[رابط]"
13
+ ],
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "strip_accents": null,
17
+ "tokenize_chinese_chars": true,
18
+ "tokenizer_class": "BertTokenizer",
19
+ "unk_token": "[UNK]",
20
+ "use_fast": true
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d353e319b858318722f42fe16a07ed1676a18eb9b65002de71a860fe206a02
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff