omarelsayeed commited on
Commit
072d609
·
1 Parent(s): 913ea2b

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. config.json +2 -1
  2. pytorch_model.bin +1 -1
  3. tokenizer.json +1 -1
  4. tokenizer_config.json +49 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "asafaya/bert-mini-arabic",
3
  "_num_labels": 2,
4
  "architectures": [
5
  "BertForSequenceClassification"
@@ -26,6 +26,7 @@
26
  "output_past": true,
27
  "pad_token_id": 0,
28
  "position_embedding_type": "absolute",
 
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.30.2",
31
  "type_vocab_size": 2,
 
1
  {
2
+ "_name_or_path": "omarelsayeed/QA_Search",
3
  "_num_labels": 2,
4
  "architectures": [
5
  "BertForSequenceClassification"
 
26
  "output_past": true,
27
  "pad_token_id": 0,
28
  "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.30.2",
32
  "type_vocab_size": 2,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deb0cfa866cb2a7c0f541a4da50cd5d27061a90c927a6606bcaab2318f495bcf
3
  size 46225679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020f8409acbcf60bf206e022aa3c5085221d151447d4d8700a140ae89c1e748c
3
  size 46225679
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 512,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 1024,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
tokenizer_config.json CHANGED
@@ -1,16 +1,65 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
  "do_basic_tokenize": true,
5
  "do_lower_case": true,
6
  "full_tokenizer_file": null,
7
  "mask_token": "[MASK]",
 
8
  "model_max_length": 1000000000000000019884624838656,
9
  "never_split": null,
 
10
  "pad_token": "[PAD]",
 
 
11
  "sep_token": "[SEP]",
 
12
  "strip_accents": null,
13
  "tokenize_chinese_chars": true,
14
  "tokenizer_class": "BertTokenizer",
 
 
15
  "unk_token": "[UNK]"
16
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "full_tokenizer_file": null,
49
  "mask_token": "[MASK]",
50
+ "max_length": 512,
51
  "model_max_length": 1000000000000000019884624838656,
52
  "never_split": null,
53
+ "pad_to_multiple_of": null,
54
  "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
  "sep_token": "[SEP]",
58
+ "stride": 0,
59
  "strip_accents": null,
60
  "tokenize_chinese_chars": true,
61
  "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
  "unk_token": "[UNK]"
65
  }