amnahhebrahim
commited on
Commit
•
95de161
1
Parent(s):
39aa870
Model save
Browse files- .gitignore +1 -0
- config.json +25 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +49 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "aubmindlab/bert-base-arabertv2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.26.1",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 64000
|
25 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12290f7e59b5bd658755f0cd4a2d680a0c642a338777849ce2d758dd470e9216
|
3 |
+
size 538486509
|
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 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"max_len": 512,
|
7 |
+
"model_max_length": 512,
|
8 |
+
"name_or_path": "aubmindlab/bert-base-arabertv2",
|
9 |
+
"never_split": [
|
10 |
+
"+ك",
|
11 |
+
"+كما",
|
12 |
+
"ك+",
|
13 |
+
"+وا",
|
14 |
+
"+ين",
|
15 |
+
"و+",
|
16 |
+
"+كن",
|
17 |
+
"+ان",
|
18 |
+
"+هم",
|
19 |
+
"+ة",
|
20 |
+
"[بريد]",
|
21 |
+
"لل+",
|
22 |
+
"+ي",
|
23 |
+
"+ت",
|
24 |
+
"+ن",
|
25 |
+
"س+",
|
26 |
+
"ل+",
|
27 |
+
"[مستخدم]",
|
28 |
+
"+كم",
|
29 |
+
"+ا",
|
30 |
+
"ب+",
|
31 |
+
"ف+",
|
32 |
+
"+نا",
|
33 |
+
"+ها",
|
34 |
+
"+ون",
|
35 |
+
"+هما",
|
36 |
+
"ال+",
|
37 |
+
"+ه",
|
38 |
+
"+هن",
|
39 |
+
"+ات",
|
40 |
+
"[رابط]"
|
41 |
+
],
|
42 |
+
"pad_token": "[PAD]",
|
43 |
+
"sep_token": "[SEP]",
|
44 |
+
"special_tokens_map_file": null,
|
45 |
+
"strip_accents": null,
|
46 |
+
"tokenize_chinese_chars": true,
|
47 |
+
"tokenizer_class": "BertTokenizer",
|
48 |
+
"unk_token": "[UNK]"
|
49 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:271eb04f0638ebac3892981b45ee3956130e78d9f12df4d8cdec3dc54a37f916
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|