razzaghi commited on
Commit
d05cb17
1 Parent(s): 7c0a23f

Upload Persian Job Classifier model

Browse files
README.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ # Persian Job Title Classifier
3
+
4
+ This model predicts ISCO codes for Persian job titles.
5
+
6
+ ## Model Details
7
+ - **Language:** Persian (Farsi)
8
+ - **Model Type:** Text classification
9
+ - **Framework:** Hugging Face Transformers
10
+ - **License:** MIT
11
+
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"hidden_activation": "ELU", "output_activation": "Softmax", "attention_dim": 128, "num_labels": 10, "loss_function": "CrossEntropyLoss", "optimizer": "AdamW", "learning_rate": 2e-05, "weight_decay": 0.01}
metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"tags": ["persian", "job-classification", "ISCO"], "datasets": ["job_titles"], "model_name": "Persian Job Classifier", "language": "fa", "library_name": "transformers", "license": "mit", "widget": [{"text": "Your sample text here"}], "loss_function": "CrossEntropyLoss"}
pytorch_job_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311a2e1d6904242aa4059f7f7baa9a12167f9a82d41a69013ad33c7c931b1d23
3
+ size 653563842
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[MASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[SEP]",
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
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff