Apizhai commited on
Commit
2125156
1 Parent(s): 426a1e6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +81 -2
README.md CHANGED
@@ -1,3 +1,82 @@
1
  ---
2
- pipeline_tag: text-classification
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - th
4
+ pipeline_tag: summarization
5
+ tags:
6
+ - text_classification
7
+ - albert
8
+ widget:
9
+ - text: >-
10
+ NairiSoft is looking for a highly qualified person
11
+ with deep knowledge and practical experience in Java programming. The
12
+ selected candidate will be involved in all stages of the development
13
+ life cycle.
14
+ example_title: Current Position Requirments 1
15
+ - text: >-
16
+ Ogma Applications is seeking motivated Senior
17
+ Developers to work on its worldwide projects. The projects are web
18
+ applications utilizing latest technologies in video webcasting over
19
+ internet for web browsers, Televisions and telephone systems.
20
+ In order to succeed in this team, the incumbent must have the passion and
21
+ energy to work in an entrepreneurial, and fast paced environment. In
22
+ addition, the Senior Software Engineer must be an experienced senior
23
+ architect and technical leader with in-depth knowledge of software
24
+ development processes.
25
+ As a senior member of the team in Armenia, Senior Software Engineer will
26
+ be working closely with other developers and peers in the US and other
27
+ teams around the globe, to analyze, design, develop, test and deliver the
28
+ best in class software.
29
+ example_title: Current Position Requirments 2
30
+
31
+ - text: >-
32
+ Armeconombank OJSC is looking for a .Net Developer to
33
+ join its team. The Software Developer will take part in design and
34
+ development projects.
35
+ example_title: Current Position Requirments 3
36
+ ---
37
+
38
+
39
+ This repository contains a Albert model designed for text classification. The architecture of the model is based on the Albert Base v2 model.
40
+
41
+ # Library
42
+
43
+ ```
44
+ pip install transformers
45
+ pip install sentencepiece
46
+ ```
47
+
48
+ # Example
49
+ ```python
50
+ from transformers import AutoModel,AutoTokenizer
51
+
52
+ tokenizer = AutoTokenizer.from_pretrained('Apizhai/Albert-IT-JobRecommendation', use_fast=False),
53
+ model = AutoModel.from_pretrained('Apizhai/Albert-IT-JobRecommendation')
54
+ ```
55
+
56
+ # Training hyperparameters
57
+ The following hyperparameters were used during training:
58
+ - max_seq_length: 128
59
+ - max_length: 128
60
+ - train_batch_size: 4
61
+ - eval_batch_size: 32
62
+ - num_train_epochs: 10
63
+ - evaluate_during_training: False
64
+ - evaluate_during_training_steps: 100
65
+ - use_multiprocessing: False
66
+ - fp16: True
67
+ - save_steps: -1
68
+ - save_eval_checkpoints: False
69
+ - save_model_every_epoch: False
70
+ - no_cache: True
71
+ - reprocess_input_data: True
72
+ - overwrite_output_dir: True
73
+ - preprocess_inputs: False
74
+ - num_return_sequences: 1
75
+
76
+ # Score
77
+ - f1-score: 0.82951
78
+ - macro avg: 0.84748
79
+ - weighted avg: 0.81575
80
+
81
+
82
+