Rahaf2001 commited on
Commit
dbc28aa
·
verified ·
1 Parent(s): 691bc5e

Upload folder using huggingface_hub

Browse files
Files changed (38) hide show
  1. Time period classification/camelbert-era-classifier.zip +3 -0
  2. Time period classification/camelbert-era-classifier/__MACOSX/._camelbert-era-classifier +0 -0
  3. Time period classification/camelbert-era-classifier/__MACOSX/camelbert-era-classifier/._config.json +0 -0
  4. Time period classification/camelbert-era-classifier/__MACOSX/camelbert-era-classifier/._era_labels.txt +0 -0
  5. Time period classification/camelbert-era-classifier/__MACOSX/camelbert-era-classifier/._model.safetensors +3 -0
  6. Time period classification/camelbert-era-classifier/__MACOSX/camelbert-era-classifier/._tokenizer.json +0 -0
  7. Time period classification/camelbert-era-classifier/__MACOSX/camelbert-era-classifier/._tokenizer_config.json +0 -0
  8. Time period classification/camelbert-era-classifier/camelbert-era-classifier/config.json +39 -0
  9. Time period classification/camelbert-era-classifier/camelbert-era-classifier/era_labels.txt +3 -0
  10. Time period classification/camelbert-era-classifier/camelbert-era-classifier/model.safetensors +3 -0
  11. Time period classification/camelbert-era-classifier/camelbert-era-classifier/tokenizer.json +0 -0
  12. Time period classification/camelbert-era-classifier/camelbert-era-classifier/tokenizer_config.json +15 -0
  13. Time period classification/config.json +39 -0
  14. Time period classification/era_labels.txt +3 -0
  15. Time period classification/era_model.ipynb +0 -0
  16. Time period classification/model.safetensors +3 -0
  17. Time period classification/tokenizer.json +0 -0
  18. Time period classification/tokenizer_config.json +15 -0
  19. Time_period_classification_Model_V2/BERTerav2-20260416T182356Z-3-001.zip +3 -0
  20. Time_period_classification_Model_V2/BERTerav2/config.json +29 -0
  21. Time_period_classification_Model_V2/BERTerav2/model.safetensors +3 -0
  22. Time_period_classification_Model_V2/BERTerav2/tokenizer.json +0 -0
  23. Time_period_classification_Model_V2/BERTerav2/tokenizer_config.json +21 -0
  24. Time_period_classification_Model_V2/BERTerav2/training_args.bin +3 -0
  25. Time_period_classification_Model_V2/Eraclassifer.ipynb +0 -0
  26. Topic_classifiication/TopicModel.ipynb +0 -0
  27. Topic_classifiication/best_model-20260416T175330Z-3-001.zip +3 -0
  28. Topic_classifiication/best_model/config.json +46 -0
  29. Topic_classifiication/best_model/label_info.pkl +3 -0
  30. Topic_classifiication/best_model/model.safetensors +3 -0
  31. Topic_classifiication/best_model/tokenizer.json +0 -0
  32. Topic_classifiication/best_model/tokenizer_config.json +21 -0
  33. Topic_classifiication/best_model/training_args.bin +3 -0
  34. config.json +61 -0
  35. labels.txt +14 -0
  36. model.safetensors +3 -0
  37. tokenizer.json +0 -0
  38. tokenizer_config.json +15 -0
Time period classification/camelbert-era-classifier.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6ffe5281862289490f47edb7da1eefa597c2d345dba213312977f06cbdf15ca
3
+ size 405265498
Time period classification/camelbert-era-classifier/__MACOSX/._camelbert-era-classifier ADDED
Binary file (176 Bytes). View file
 
Time period classification/camelbert-era-classifier/__MACOSX/camelbert-era-classifier/._config.json ADDED
Binary file (176 Bytes). View file
 
Time period classification/camelbert-era-classifier/__MACOSX/camelbert-era-classifier/._era_labels.txt ADDED
Binary file (176 Bytes). View file
 
Time period classification/camelbert-era-classifier/__MACOSX/camelbert-era-classifier/._model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4cc8aab155bd9fce77f27cba1087d98f3b5966b33be37efa313f4959855a5f
3
+ size 176
Time period classification/camelbert-era-classifier/__MACOSX/camelbert-era-classifier/._tokenizer.json ADDED
Binary file (176 Bytes). View file
 
Time period classification/camelbert-era-classifier/__MACOSX/camelbert-era-classifier/._tokenizer_config.json ADDED
Binary file (176 Bytes). View file
 
Time period classification/camelbert-era-classifier/camelbert-era-classifier/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "LABEL_0",
17
+ "1": "LABEL_1",
18
+ "2": "LABEL_2"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "is_decoder": false,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "max_position_embeddings": 512,
30
+ "model_type": "bert",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 0,
34
+ "tie_word_embeddings": true,
35
+ "transformers_version": "5.0.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": false,
38
+ "vocab_size": 30000
39
+ }
Time period classification/camelbert-era-classifier/camelbert-era-classifier/era_labels.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ قديم
2
+ وسيط
3
+ حديث
Time period classification/camelbert-era-classifier/camelbert-era-classifier/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a017935e208cd28f19e610037910fdb18ff9903ec921d0e60cfc1757d3f4bb57
3
+ size 436358108
Time period classification/camelbert-era-classifier/camelbert-era-classifier/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Time period classification/camelbert-era-classifier/camelbert-era-classifier/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "full_tokenizer_file": null,
6
+ "is_local": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
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
+ }
Time period classification/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "LABEL_0",
17
+ "1": "LABEL_1",
18
+ "2": "LABEL_2"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "is_decoder": false,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "max_position_embeddings": 512,
30
+ "model_type": "bert",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 0,
34
+ "tie_word_embeddings": true,
35
+ "transformers_version": "5.0.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": false,
38
+ "vocab_size": 30000
39
+ }
Time period classification/era_labels.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ قديم
2
+ وسيط
3
+ حديث
Time period classification/era_model.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
Time period classification/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a017935e208cd28f19e610037910fdb18ff9903ec921d0e60cfc1757d3f4bb57
3
+ size 436358108
Time period classification/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Time period classification/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "full_tokenizer_file": null,
6
+ "is_local": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
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
+ }
Time_period_classification_Model_V2/BERTerav2-20260416T182356Z-3-001.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b518da705b634274a107f359f38a982de591b84fbe8e9bf835b0c160d80e22ec
3
+ size 502654001
Time_period_classification_Model_V2/BERTerav2/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": 64000
29
+ }
Time_period_classification_Model_V2/BERTerav2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d11e65f66639be4a54c46704a227de6f8acdd8bc6712331c799d558cfe4fec
3
+ size 540803048
Time_period_classification_Model_V2/BERTerav2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Time_period_classification_Model_V2/BERTerav2/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "is_local": false,
7
+ "mask_token": "[MASK]",
8
+ "max_len": 512,
9
+ "model_max_length": 512,
10
+ "never_split": [
11
+ "[بريد]",
12
+ "[مستخدم]",
13
+ "[رابط]"
14
+ ],
15
+ "pad_token": "[PAD]",
16
+ "sep_token": "[SEP]",
17
+ "strip_accents": null,
18
+ "tokenize_chinese_chars": true,
19
+ "tokenizer_class": "BertTokenizer",
20
+ "unk_token": "[UNK]"
21
+ }
Time_period_classification_Model_V2/BERTerav2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea817d048a3a19b567f5fc854c933124083537dd06f7827ab34f2fd8ad7e491f
3
+ size 5201
Time_period_classification_Model_V2/Eraclassifer.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
Topic_classifiication/TopicModel.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
Topic_classifiication/best_model-20260416T175330Z-3-001.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55916e4507e95f8c8dcdb0153a0316ff44f8f6a5a5b263d8271aed47420ee0a5
3
+ size 502676405
Topic_classifiication/best_model/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
15
+ "0": "\u062f\u064a\u0646\u064a\u0629",
16
+ "1": "\u0631\u062b\u0627\u0621",
17
+ "2": "\u063a\u0632\u0644_\u0631\u0648\u0645\u0627\u0646\u0633\u064a",
18
+ "3": "\u0645\u062f\u062d",
19
+ "4": "\u0647\u062c\u0627\u0621_\u0630\u0645",
20
+ "5": "\u0648\u062c\u062f\u0627\u0646\u064a",
21
+ "6": "\u0648\u0637\u0646\u064a\u0629"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "is_decoder": false,
26
+ "label2id": {
27
+ "\u062f\u064a\u0646\u064a\u0629": 0,
28
+ "\u0631\u062b\u0627\u0621": 1,
29
+ "\u063a\u0632\u0644_\u0631\u0648\u0645\u0627\u0646\u0633\u064a": 2,
30
+ "\u0645\u062f\u062d": 3,
31
+ "\u0647\u062c\u0627\u0621_\u0630\u0645": 4,
32
+ "\u0648\u062c\u062f\u0627\u0646\u064a": 5,
33
+ "\u0648\u0637\u0646\u064a\u0629": 6
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "tie_word_embeddings": true,
42
+ "transformers_version": "5.0.0",
43
+ "type_vocab_size": 2,
44
+ "use_cache": false,
45
+ "vocab_size": 64000
46
+ }
Topic_classifiication/best_model/label_info.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f095b5dd3e52136d6965b639c79b2bd6c7da7e8be30056fee0c09a01a6f462cb
3
+ size 542
Topic_classifiication/best_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a18427e55a3faaffe803c2acd5422cfc2be96bedd9f0bb1449de0e3b75ed67
3
+ size 540818452
Topic_classifiication/best_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Topic_classifiication/best_model/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "is_local": false,
7
+ "mask_token": "[MASK]",
8
+ "max_len": 512,
9
+ "model_max_length": 512,
10
+ "never_split": [
11
+ "[بريد]",
12
+ "[مستخدم]",
13
+ "[رابط]"
14
+ ],
15
+ "pad_token": "[PAD]",
16
+ "sep_token": "[SEP]",
17
+ "strip_accents": null,
18
+ "tokenize_chinese_chars": true,
19
+ "tokenizer_class": "BertTokenizer",
20
+ "unk_token": "[UNK]"
21
+ }
Topic_classifiication/best_model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73e6ac9eacf3c2617b863a907d6dd1a1be000cf0df3cf7dfd565b45d6f378eca
3
+ size 5201
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5",
21
+ "6": "LABEL_6",
22
+ "7": "LABEL_7",
23
+ "8": "LABEL_8",
24
+ "9": "LABEL_9",
25
+ "10": "LABEL_10",
26
+ "11": "LABEL_11",
27
+ "12": "LABEL_12",
28
+ "13": "LABEL_13"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "is_decoder": false,
33
+ "label2id": {
34
+ "LABEL_0": 0,
35
+ "LABEL_1": 1,
36
+ "LABEL_10": 10,
37
+ "LABEL_11": 11,
38
+ "LABEL_12": 12,
39
+ "LABEL_13": 13,
40
+ "LABEL_2": 2,
41
+ "LABEL_3": 3,
42
+ "LABEL_4": 4,
43
+ "LABEL_5": 5,
44
+ "LABEL_6": 6,
45
+ "LABEL_7": 7,
46
+ "LABEL_8": 8,
47
+ "LABEL_9": 9
48
+ },
49
+ "layer_norm_eps": 1e-12,
50
+ "max_position_embeddings": 32,
51
+ "model_type": "bert",
52
+ "num_attention_heads": 12,
53
+ "num_hidden_layers": 10,
54
+ "pad_token_id": 0,
55
+ "position_embedding_type": "absolute",
56
+ "tie_word_embeddings": true,
57
+ "transformers_version": "5.0.0",
58
+ "type_vocab_size": 2,
59
+ "use_cache": false,
60
+ "vocab_size": 50000
61
+ }
labels.txt ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ saree
2
+ kamel
3
+ mutakareb
4
+ mutadarak
5
+ munsareh
6
+ madeed
7
+ mujtath
8
+ ramal
9
+ baseet
10
+ khafeef
11
+ taweel
12
+ wafer
13
+ hazaj
14
+ rajaz
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b236d99219dd8fe710a09a2807edc05b2bd2936d02424a7959e03fceb0279ea4
3
+ size 439650624
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "is_local": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 32,
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
+ }