Alasil commited on
Commit
369df62
·
verified ·
1 Parent(s): ab01865

[Run 20260606_003313] Upload model weights

Browse files
models/aubmindlab_bert-base-arabertv2/20260606_003313/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": "5.9.0",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 64000
29
+ }
models/aubmindlab_bert-base-arabertv2/20260606_003313/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af23a228a16b17b5ed2b16cc3b4762cd97bdb4884793828dcc6f2c02be704a45
3
+ size 540803072
models/aubmindlab_bert-base-arabertv2/20260606_003313/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models/aubmindlab_bert-base-arabertv2/20260606_003313/tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_len": 512,
10
+ "model_max_length": 512,
11
+ "never_split": [
12
+ "+ك",
13
+ "+كما",
14
+ "ك+",
15
+ "+وا",
16
+ "+ين",
17
+ "و+",
18
+ "+كن",
19
+ "+ان",
20
+ "+هم",
21
+ "+ة",
22
+ "[بريد]",
23
+ "لل+",
24
+ "+ي",
25
+ "+ت",
26
+ "+ن",
27
+ "س+",
28
+ "ل+",
29
+ "[مستخدم]",
30
+ "+كم",
31
+ "+ا",
32
+ "ب+",
33
+ "ف+",
34
+ "+نا",
35
+ "+ها",
36
+ "+ون",
37
+ "+هما",
38
+ "ال+",
39
+ "+ه",
40
+ "+هن",
41
+ "+ات",
42
+ "[رابط]"
43
+ ],
44
+ "pad_token": "[PAD]",
45
+ "sep_token": "[SEP]",
46
+ "strip_accents": null,
47
+ "tokenize_chinese_chars": true,
48
+ "tokenizer_class": "BertTokenizer",
49
+ "unk_token": "[UNK]"
50
+ }